Menu
▾
▴
dl-learner-discussion — DL-Learner related discussions
You can subscribe to this list here.
| 2007 |
Jan
|
Feb
|
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
(2) |
Sep
|
Oct
|
Nov
|
Dec
|
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2008 |
Jan
|
Feb
(1) |
Mar
(1) |
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2009 |
Jan
|
Feb
|
Mar
(11) |
Apr
(1) |
May
(1) |
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2010 |
Jan
|
Feb
(7) |
Mar
|
Apr
(2) |
May
|
Jun
(3) |
Jul
|
Aug
(2) |
Sep
(3) |
Oct
|
Nov
|
Dec
|
| 2011 |
Jan
|
Feb
|
Mar
(3) |
Apr
(7) |
May
(3) |
Jun
(2) |
Jul
(12) |
Aug
(19) |
Sep
(3) |
Oct
(8) |
Nov
(6) |
Dec
(1) |
| 2012 |
Jan
(17) |
Feb
|
Mar
(7) |
Apr
(7) |
May
(1) |
Jun
(5) |
Jul
(1) |
Aug
|
Sep
(2) |
Oct
(3) |
Nov
(2) |
Dec
|
| 2013 |
Jan
|
Feb
|
Mar
|
Apr
|
May
(2) |
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
| 2014 |
Jan
(2) |
Feb
(5) |
Mar
(1) |
Apr
(7) |
May
(4) |
Jun
(1) |
Jul
|
Aug
|
Sep
|
Oct
(2) |
Nov
|
Dec
(5) |
| 2015 |
Jan
(2) |
Feb
(6) |
Mar
(2) |
Apr
(7) |
May
|
Jun
|
Jul
(3) |
Aug
|
Sep
|
Oct
|
Nov
|
Dec
(1) |
| 2016 |
Jan
(9) |
Feb
(5) |
Mar
|
Apr
|
May
(2) |
Jun
(2) |
Jul
|
Aug
|
Sep
|
Oct
(1) |
Nov
|
Dec
(3) |
| 2017 |
Jan
(2) |
Feb
|
Mar
(9) |
Apr
(3) |
May
(13) |
Jun
(2) |
Jul
|
Aug
|
Sep
(1) |
Oct
(4) |
Nov
|
Dec
(2) |
| 2018 |
Jan
(1) |
Feb
(2) |
Mar
|
Apr
|
May
|
Jun
|
Jul
|
Aug
|
Sep
|
Oct
|
Nov
|
Dec
|
|
From: Patrick W. <pat...@in...> - 2017-04-20 10:42:48
|
Hi Faranak, sorry we forgot you. Referring back to your question, why you got differing results running DL-Learner directly and invoking it from within Protégé, we cannot really give a good answer without having an example to reproduce this. I can only point to the code where the Protégé plugin initializes the learning algorithm [0], the learning problem [1], and the reasoner component [2]. It might be that this already differs from the settings you made in your configuration file/Java code. Apart from this I don't see any specific differences. (But I'm also not too familiar with the Protégé plugin.) [0] https://github.com/AKSW/DL-Learner-Protege-Plugin/blob/master/src/main/java/org/dllearner/tools/protege/Manager.java#L167-L198 [1] https://github.com/AKSW/DL-Learner-Protege-Plugin/blob/master/src/main/java/org/dllearner/tools/protege/Manager.java#L200-L211 [2] https://github.com/AKSW/DL-Learner-Protege-Plugin/blob/master/src/main/java/org/dllearner/tools/protege/Manager.java#L218-L233 On 03/13/2017 11:46 AM, Faranak Sobhani wrote: > Dear Simon, > > Sorry to be a bother! > > > Thanks a lot. > > > Best, > > Faranak > > > > -- > *Faranak Sobhani* > PhD Electronic Engineering Student > *MMV (Multimedia and Vision) Lab* > School of Electronic Engineering and Computer Science > Queen Mary University of London > Mile End Road, London E1 4NS, UK > > > > ------------------------------------------------------------------------ > *From:* Simon Bin <sb...@in...> > *Sent:* 13 March 2017 10:37 > *To:* Faranak Sobhani; dl-...@li... > *Subject:* Re: Fwd: Re: Dl-Learner > > Dear Faranak > > please send further Replies to > <dl-...@li...> > > (use Reply All or Reply to List button in your Mail program) > > It does not make any sense that you send the same email to 4 People and > receive 4 independent replies. > > Thanks, > > On Mon, 2017-03-13 at 09:53 +0000, Faranak Sobhani wrote: >> Dear Simon, >> >> Thank you very much for getting beck to me. >> >> >> The reason I can not share the ontology is, it is part of the project and I am somehow using that for my research as well. This is the only reason as this version hasn't publish yet. >> >> >> What I mean exactly is the result I'm getting from protege is different with what I get from code and by coding I just get results which is not that much helpful for me. >> >> To make it more clear in the following example I did use the same (.owl ) file and the first solution is what I got from source code(.java) and the second one from protege. >> >> >> From Code; >> >> solutions: >> 1: isFrom only SpatioTemporalParticular 54.24% >> 2: isFrom only Particular 54.24% >> 3: Thing 50.85% >> 4: Stative 50.85% >> 5: SpatioTemporalParticular 50.85% >> 6: PhysicalAggression 50.85% >> 7: Perdurant 50.85% >> 8: Particular 50.85% >> 9: GlobalPerdurant 50.85% >> 10: Activities 50.85% >> 11: ActivePhysicalAggresion 50.85% >> 12: isFrom some Thing 50.85% >> 13: Particular or TimeDifference 50.85% >> 14: GlobalPerdurant or TimeDifference 50.85% >> 15: GlobalPerdurant or Particular 50.85% >> 16: DistanceToAParticular or Particular 50.85% >> 17: DistanceToAParticular or GlobalPerdurant 50.85% >> >> >> >> From Protege ; >> [cid:06f8e3a3-930e-48c0-8075-bb00b55572da] >> >> >> As you can see by protege more properties involved and for some unknown reason I'm not able to get the relation when I run the java code. >> Is there any specific setting I need to change in the code or any suggestion that I can have the properties involved? >> >> >> >> I am using positive example only, I mean considering only the instances of the target class. In other words, I do have a Target class and all related instance for that class and based on these instances I'm trying to learn the definition of the class. >> >> >> If my explanation is still not clear that you can somehow help me based on them, as you did suggest I will create some example data and share the JAVA Code Example. >> >> >> Appreciate you consideration and help. >> >> >> -- >> Faranak Sobhani >> PhD Electronic Engineering Student >> MMV (Multimedia and Vision) Lab >> School of Electronic Engineering and Computer Science >> Queen Mary University of London >> Mile End Road, London E1 4NS, UK >> >> >> >> ________________________________ >> From: Simon Bin <sb...@in...> >> Sent: 13 March 2017 09:36 >> To: Faranak Sobhani >> Cc: Lorenz B.; Patrick Westphal >> Subject: Re: Fwd: Re: Dl-Learner >> >> Dear Faranak, >> >> maybe you can at least share your JAVA Code Example with us? >> >> Since you cannot provide the ontology, can you tell us more about the >> Classes and Properties in it? Is there a Class Hierarchy >> (subClassOf...?) Can you describe the structure of the data? Maybe you >> can create some fake example data for one or two instances? >> >> Are you using the DL-Learner with Positive and Negative examples or >> Concept learning? You can also try to increase the >> maxExecutionTimeInSeconds in case time would be the limiting factor. >> >> Cheers, >> Simon >> >> >> On Mon, 2017-03-13 at 09:55 +0100, Lorenz B. wrote: >> > >> > >> > -------- Forwarded Message -------- >> > Subject: Re: Dl-Learner >> > Date: Fri, 10 Mar 2017 12:46:22 +0000 >> > From: Faranak Sobhani <f.s...@qm...> >> > To: Lorenz B. <bue...@in...> >> > >> > >> > >> > Dear Professor, >> > >> > Sorry for disturbing again. >> > I got stuck in some experiments with DL-Learner and can not proceed. >> > >> > Firstly I did try with Protege DL plugin out of 7 concepts, for 4 >> > concepts I got the really good results (solution) but then when I did >> > use the source code(CELOE.java) to check whether I would be able to have >> > solutions for the other 3Concepts- I faced with the problem that for >> > every concept I can get the solution like following; >> > >> > >> > solutions: >> > 1: Stative 85.96% >> > 2: Activities 85.96% >> > 3: Thing 19.30% >> > 4: SpatioTemporalParticular 19.30% >> > 5: Perdurant 19.30% >> > 6: Particular 19.30% >> > 7: GlobalPerdurant 19.30% >> > 8: Event 19.30% >> > >> > >> > >> > I did try the code with several provide (.owl) examples. For all of >> > them, it works and I can get resealable solutions such as following. >> > >> > solutions: >> > 1: getsRingReplacedAtPosition some Thing 100.00% >> > 2: (getsReplacedBy some Substituent) and (getsRingReplacedAtPosition >> > some Thing) 100.00% >> > 3: (Drug or Substituent) and (getsReplacedBy some Substituent) 100.00% >> > 4: (Drug or Size) and (getsReplacedBy some Substituent) 100.00% >> > 5: (Drug or Sigma) and (getsReplacedBy some Substituent) 100.00% >> > 6: (Drug or Polar) and (getsReplacedBy some Substituent) 100.00% >> > 7: (Drug or PiDonor) and (getsReplacedBy some Substituent) 100.00% >> > 8: (Drug or PiAcceptor) and (getsReplacedBy some Substituent) 100.00% >> > 9: (Drug or HDonor) and (getsReplacedBy some Substituent) 100.00% >> > >> > I went through code several times and it is really not clear for me how >> > I can fix this problem, I did try to debug line by line -seems like >> > there is a secret solution for that that I can not get it really. >> > >> > >> > I was wondering if there is any limitation in terms of a number of >> > concept or object hierarchy? As when I am trying each concept >> > individually in a separate .owl file I can have good solutions, but when >> > I add them to my ontology with the following metric I can't get any >> > solutions. >> > >> > >> > Following is my ontology metrics; >> > Axiom9999 >> > Logical axiom count7375 >> > Declaration axioms count2453 >> > Class count482 >> > Object property count148 >> > Data property count55 >> > Individual count1763 >> > >> > Any chance you can help me with this problem PLEASE? >> > >> > Your support would be greatly appreciated. >> > >> > Best, >> > Faranak >> > >> > >> > -- >> > *Faranak Sobhani* >> > PhD Electronic Engineering Student >> > *MMV (Multimedia and Vision) Lab* >> > School of Electronic Engineering and Computer Science >> > Queen Mary University of London >> > Mile End Road, London E1 4NS, UK >> > >> > >> > >> > ------------------------------------------------------------------------ >> > *From:* Lorenz B. <bue...@in...> >> > *Sent:* 15 February 2017 11:12 >> > *To:* Faranak Sobhani >> > *Subject:* Re: Dl-Learner >> > >> > Hello Faranak, >> > >> > can you share the ontology with us and maybe also give us a descriptions >> > of the steps you did? >> > >> > >> > >> > Cheers, >> > Lorenz >> > >> > > Dear Professor, >> > > >> > > Sorry to be a bother as, I said previously, I'm working on ontology >> > > learning and currently focusing on DL-learner. >> > > I came across few issues that I would be grateful if you could help me >> > > over them *PLEASE*. >> > > >> > > I am using protege 5.1 with the latest available version of the >> > > DL-Learner, for some unknown reason each time I run the reasoner and >> > > selecting the suggestion for equivalence class ( I choose EL profile >> > > from the setting section ) for the same concept I get different >> > > hypothesis without even changing the setting. >> > > More importantly, for most of my main concept(which I want to focus >> > > on them more) I have the following error which is not really clear >> > > for me >> > > >> > > * Level: ERROR Time: 1487097022334 Message: An error was thrown: >> > > CELOE could not find any node with lesser accuracy. >> > > java.lang.RuntimeException StackTrace: >> > > org.dllearner.algorithms.celoe.CELOE.getNextNodeToExpand(CELOE.java:484) >> > > org.dllearner.algorithms.celoe.CELOE.start(CELOE.java:333) >> > > org.dllearner.tools.protege.Manager.startLearning(Manager.java:320) >> > > org.dllearner.tools.protege.ActionHandler$SuggestionRetriever.doInBackground(ActionHandler.java:240) >> > > org.dllearner.tools.protege.ActionHandler$SuggestionRetriever.doInBackground(ActionHandler.java:184) >> > > javax.swing.SwingWorker$1.call(SwingWorker.java:295) >> > > java.util.concurrent.FutureTask.run(FutureTask.java:266) >> > > javax.swing.SwingWorker.run(SwingWorker.java:334) >> > > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) >> > > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) >> > > java.lang.Thread.run(Thread.java:745) >> > > * >> > > >> > > Your support would be greatly appreciated. >> > > Best, >> > > Faranak >> > > >> > > >> > > -- >> > > *Faranak Sobhani* >> > > PhD Electronic Engineering Student >> > > *MMV (Multimedia and Vision) Lab* >> > > School of Electronic Engineering and Computer Science >> > > Queen Mary University of London >> > > Mile End Road, London E1 4NS, UK >> > > >> > > >> > > >> > > ------------------------------------------------------------------------ >> > > *From:* Lorenz B. <bue...@in...> >> > > *Sent:* 02 November 2016 08:46 >> > > *To:* Faranak Sobhani >> > > *Subject:* Re: Dl-Learner >> > > >> > > Hello Faranak, >> > > >> > > from the exceptions it looks like you have multiple version of the >> > > plugin installed. Can you please remove all DL-Learner libs first? If >> > > you use Windows, I don't know which folders you have to cleanup. >> > > >> > > >> > > And please don't use Protege 5.0 beta anymore. There is already 5.1.0 >> > > released. >> > > >> > > >> > > >> > > >> > > Kind regards, >> > > Lorenz >> > > >> > > > Hi, >> > > > >> > > > Yes , I did place it in the Plugin folder. >> > > > >> > > > >> > > > The first attache(DownloadPlugin.txt) is when I download Plugin and >> > > > the second on is when I want to add it from File in >> > > > protege(AddFromProtege.txt) >> > > > >> > > > >> > > > Best, >> > > > >> > > > Faranak >> > > > >> > > > >> > > > >> > > > -- >> > > > *Faranak Sobhani* >> > > > PhD Electronic Engineering Student >> > > > *MMV (Multimedia and Vision) Lab* >> > > > School of Electronic Engineering and Computer Science >> > > > Queen Mary University of London >> > > > Mile End Road, London E1 4NS, UK >> > > > >> > > > >> > > > >> > > > ------------------------------------------------------------------------ >> > > > *From:* Lorenz B. <bue...@in...> >> > > > *Sent:* 01 November 2016 11:25 >> > > > *To:* Faranak Sobhani >> > > > *Subject:* Re: Dl-Learner >> > > > >> > > > Hello Faranak, >> > > > >> > > > where did you put the JAR file? It has to be in the 'plugins' folder. >> > > > Can you attach the log messages from the start of Protege? This >> > > > should show every working plugin. And also error messages. >> > > > >> > > > >> > > > >> > > > Kind regards, >> > > > Lorenz >> > > > >> > > > > Thank you very much for getting back to me. >> > > > > >> > > > > >> > > > > I have used the attached Plugin both for protege 4.3 and 5 and I did >> > > > > the steps as it is mentioned in read me! But after choosing the >> > > > > class in the class hierarchy view and selecting the equivalence tab, >> > > > > can't see the DL-Learner tab . I just have the same 4 tabs as I had >> > > > > previously ( Object restriction, Data restriction, Class hierarchy >> > > > > and class expression editor). >> > > > > >> > > > > >> > > > > Can you please kindly help me over that . ( Where do you see the >> > > > > problem? ) >> > > > > >> > > > > >> > > > > Would be really kind of you if sending me the protege version which >> > > > > works for you, although I have used both 4.3 and 5 downloaded from >> > > > > the protege site ! >> > > > > >> > > > > >> > > > > Best, >> > > > > >> > > > > Faranak >> > > > > >> > > > > >> > > > > -- >> > > > > *Faranak Sobhani* >> > > > > PhD Electronic Engineering Student >> > > > > *MMV (Multimedia and Vision) Lab* >> > > > > School of Electronic Engineering and Computer Science >> > > > > Queen Mary University of London >> > > > > Mile End Road, London E1 4NS, UK >> > > > > >> > > > > >> > > > > >> > > > > ------------------------------------------------------------------------ >> > > > > *From:* Lorenz B. <bue...@in...> >> > > > > *Sent:* 28 October 2016 12:46 >> > > > > *To:* Faranak Sobhani >> > > > > *Cc:* Jens Lehmann >> > > > > *Subject:* Re: Dl-Learner >> > > > > >> > > > > Dear Farank, >> > > > > >> > > > > not sure why it did not work for you, but we created a new >> > > > > pre-release right now [1]. This worked for me with latest Protege >> > > > > 5.1.0. Let us know if something does not work. >> > > > > >> > > > > Note, that we also updated the README such that you can find the >> > > > > DL-Learner tab easier. Probably the previous documentation was a bit >> > > > > misleading as the DL-Learner plugin is just a tab in a specific view >> > > > > and not a proper Protege tab like other plugins provide. >> > > > > >> > > > > We will also try to make the plugin available via the Protege plugin >> > > > > library feature, but this might take some time as we have to contact >> > > > > the maintainer first. >> > > > > >> > > > > >> > > > > [1] >> > > > > https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1 > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > > AKSW/DL-Learner-Protege-Plugin > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > >> >> [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; >> >> AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> >> github.com >> DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework >> >> >> >> > > > > >> > > > > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > > AKSW/DL-Learner-Protege-Plugin > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > >> >> [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; >> >> AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> >> github.com >> DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework >> >> >> >> > > > > >> > > > > AKSW/DL-Learner-Protege-Plugin >> > > > > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > > AKSW/DL-Learner-Protege-Plugin > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > >> >> [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; >> >> AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> >> github.com >> DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework >> >> >> >> > > > > github.com >> > > > > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner >> > > > > framework >> > > > > >> > > > > >> > > > > >> > > > > >> > > > > >> > > > > Kind regards, >> > > > > Lorenz >> > > > > >> > > > > > >> > > > > > -------- Ursprüngliche Nachricht -------- >> > > > > > Von: Faranak Sobhani <f.s...@qm...> >> > > > > > Datum: 27.10.16 21:21 (GMT+01:00) >> > > > > > An: jen...@cs... >> > > > > > Betreff: Dl-Learner >> > > > > > >> > > > > > Dear Professor, >> > > > > > >> > > > > > I am a PhD student working on Knowledge representation. >> > > > > > >> > > > > > I am trying to use Dl-Learner-Protege-Plugin, But for some unknown >> > > > > > reason I am not able to work with that. >> > > > > > >> > > > > > >> > > > > > Basically, I did try both operations; Downloading the plugin from >> > > > > > the "http://dl-learner.org/community/protege-plugin/" and also use >> >> Protégé Plugin<http://dl-learner.org/community/protege-plugin/> > Protégé Plugin <http://dl-learner.org/community/protege-plugin/> > dl-learner.org > Protégé DL-Learner Plugin. The Protégé 4 DL-Learner plugin allows to > learn equivalence and super class axioms based on the instance data in > the ontologies loaded ... > > > >> dl-learner.org >> Protégé DL-Learner Plugin. The Protégé 4 DL-Learner plugin allows to learn equivalence and super class axioms based on the instance data in the ontologies loaded ... >> >> >> >> > > > > > from the “File“ => “Preferences“ => “Plugins“. >> > > > > > >> > > > > > >> > > > > > I used the download file both for protege 4.3 and 5. However, can >> > > > > > not have the Dl-learner tab. Also, from the second option, when I >> > > > > > use the protege 4.3 "checking for downloads" tab, it tells me >> > > > > > there is no update and when I use from protege 5, I can see the >> > > > > > DL-Learner version 8 , but after installing it gives me an error of >> > > > > > " some error found downloading plugin" >> > > > > > >> > > > > > >> > > > > > Can you please kindly help me over that. >> > > > > > >> > > > > > >> > > > > > Best, >> > > > > > >> > > > > > Faranak >> > > > > > >> > > > > > >> > > > > > >> > > > > > -- >> > > > > > *Faranak Sobhani* >> > > > > > PhD Electronic Engineering Student >> > > > > > *MMV (Multimedia and Vision) Lab* >> > > > > > School of Electronic Engineering and Computer Science >> > > > > > Queen Mary University of London >> > > > > > Mile End Road, London E1 4NS, UK >> > > > > > >> > > > > >> > > > > -- >> > > > > Lorenz Bühmann >> > > > > AKSW group, University of Leipzig >> > > > > Group: http://aksw.org - semantic web research center > Agile Knowledge Engineering and Semantic Web (AKSW ... <http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by > Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We > are happy to announce ... > > > >> >> Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> > Agile Knowledge Engineering and Semantic Web (AKSW ... <http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by > Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We > are happy to announce ... > > > >> aksw.org >> The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... >> >> >> >> > > > >> > > > -- >> > > > Lorenz Bühmann >> > > > AKSW group, University of Leipzig >> > > > Group: http://aksw.org - semantic web research center > Agile Knowledge Engineering and Semantic Web (AKSW ... <http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by > Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We > are happy to announce ... > > > >> >> Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> > Agile Knowledge Engineering and Semantic Web (AKSW ... <http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by > Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We > are happy to announce ... > > > >> aksw.org >> The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... >> >> >> >> > > >> > > -- >> > > Lorenz Bühmann >> > > AKSW group, University of Leipzig >> > > Group: http://aksw.org - semantic web research center > Agile Knowledge Engineering and Semantic Web (AKSW ... <http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by > Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We > are happy to announce ... > > > >> >> Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> > Agile Knowledge Engineering and Semantic Web (AKSW ... <http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by > Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We > are happy to announce ... > > > >> aksw.org >> The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... >> >> >> >> > >> > > > > ------------------------------------------------------------------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, Slashdot.org! http://sdm.link/slashdot > > > > _______________________________________________ > dl-learner-discussion mailing list > dl-...@li... > https://lists.sourceforge.net/lists/listinfo/dl-learner-discussion > -- Patrick Westphal Department of Computer Science, University of Leipzig Research Group: http://aksw.org/ Phone: +49-341-9732305 |
|
From: Patrick W. <pat...@in...> - 2017-04-20 10:27:27
|
Hi Luis, first of all sorry for the late reply. I looked into your example and it seems the main problem is, that the parameter frequencyThreshold on the operator is not set explicitly. By default it is 3 and there is a check [0] whether a certain value of a property appears significantly often to be considered for a hasValue refinement. In your case livesIn(X,water) and livesIn(X,earth) each appear only once s.t. both are discarded since their number of appearances is below the frequencyThreshold of 3. If you set frequencyThreshold to 1 (or add further examples) you should get a 100% accurate result for your example setup. [0] https://github.com/AKSW/DL-Learner/blob/develop/components-core/src/main/java/org/dllearner/refinementoperators/RhoDRDown.java#L322-L323 On 04/13/2017 04:25 PM, palacios wrote: > Hello, > > I am a PhD student at the Université Paris-Sud, France. We are > interested on applying concept learning. > > For this task, we were looking into DL-Learner since it has a long > trajectory and solid in the topic. > I have downloaded the last stand-alone version, and based my test on the > examples and documentation you give. > We are specially interested in learning concepts considering the > HasValue constructor. > > For our running tests, we simplified the ontology to the following: > > Animal(Cat),Animal(Fish) > Environment(Earth),Environment(Water) > livesIn(Cat,Eart),livesIn(Fish,Water) > > And gave Cat as a positive example and Fish as a negative one. > Thus we expected to learn concepts like: > > livesIn value {Earth} > > But instead I get results of the form: > 14:39:51,305 CELOE - solutions: > 1: Thing (pred. acc.: 50.00%, F-measure: 66.67%) > 2: Animal (pred. acc.: 50.00%, F-measure: 66.67%) > 3: livesIn some Environment (pred. acc.: 50.00%, F-measure: 66.67%) > 4: Animal or Environment (pred. acc.: 50.00%, F-measure: 66.67%) > 5: Environment or (livesIn some Environment) (pred. acc.: 50.00%, > F-measure: 66.67%) > 6: Animal or (not (livesIn some Thing)) (pred. acc.: 50.00%, F-measure: > 66.67%) > 7: Animal and (Environment or (livesIn some Environment)) (pred. acc.: > 50.00%, F-measure: 66.67%) > 8: (not (livesIn some Thing)) or (livesIn some Environment) (pred. acc.: > 50.00%, F-measure: 66.67%) > 9: Animal or (Environment and (not (livesIn some Thing))) (pred. acc.: > 50.00%, F-measure: 66.67%) > 10: Animal or Environment or (not (livesIn some Thing)) (pred. acc.: > 50.00%, F-measure: 66.67%) > > As you can see it never gets to use the hasValue constructor. For the > configuration file, I have used: > > prefixes = [ ("ex”,”prefix#”) ] > ks.type = "OWL File" > ks.fileName = "toyLearner.owl" > reasoner.type = "fast instance checker" > reasoner.sources = {ks} > lp.reasoner = reasoner > lp.type = "posNegStandard" > lp.positiveExamples = {"ex:Cat"} > lp.negativeExamples = {"ex:Fish"} > op.type = "rho" > op.useNegation = false > op.useCardinalityRestrictions = false > op.useHasValueConstructor = true > alg.type = "celoe" > alg.maxExecutionTimeInSeconds = 60 > alg.noisePercentage = 0.0 > alg.reasoner = reasoner > > Additionally on more complex ontologies, the algorithm does not seem to > search for too specific expressions, meaning that instead of > specializing a expression (trough conjunctions) it always prefers to > make disjunctions. I suppose this part has to do with the breadth search > preferences (which is maybe preventing it from using the HasValue > constructor as well?), but I didn’t find how to set this parameter. > > I have looked into the online documentation, and in the sample files you > provide but I could not get further. > > If you could point out where should I change the file, or where to look > on how to properly set the parameters for using HasValue and controlling > the depth/breadth of the search, I would appreciate it. > > Finally, many of the expressions use “ConceptA or ConceptB” as an > answer. Since only one part of the disjunction has to be true, if the > other part covers no examples at all, the algorithm still considers it > in the possible answer (eg. Animal or Environment, since Environment > covers 0% of the samples, I would like this concept to be excluded from > the answers provided, i.e. is trivial compared to answer 2. Animal). Is > there a way to control this behavior? > > Thanks in advance, > Luis > > > ------------------------------------------------------------------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, Slashdot.org! http://sdm.link/slashdot > _______________________________________________ > dl-learner-discussion mailing list > dl-...@li... > https://lists.sourceforge.net/lists/listinfo/dl-learner-discussion > -- Patrick Westphal Department of Computer Science, University of Leipzig Research Group: http://aksw.org/ Phone: +49-341-9732305 |
|
From: palacios <lui...@lr...> - 2017-04-13 14:45:21
|
Hello,
I am a PhD student at the Université Paris-Sud, France. We are
interested on applying concept learning.
For this task, we were looking into DL-Learner since it has a long
trajectory and solid in the topic.
I have downloaded the last stand-alone version, and based my test on the
examples and documentation you give.
We are specially interested in learning concepts considering the
HasValue constructor.
For our running tests, we simplified the ontology to the following:
Animal(Cat),Animal(Fish)
Environment(Earth),Environment(Water)
livesIn(Cat,Eart),livesIn(Fish,Water)
And gave Cat as a positive example and Fish as a negative one.
Thus we expected to learn concepts like:
livesIn value {Earth}
But instead I get results of the form:
14:39:51,305 CELOE - solutions:
1: Thing (pred. acc.: 50.00%, F-measure: 66.67%)
2: Animal (pred. acc.: 50.00%, F-measure: 66.67%)
3: livesIn some Environment (pred. acc.: 50.00%, F-measure: 66.67%)
4: Animal or Environment (pred. acc.: 50.00%, F-measure: 66.67%)
5: Environment or (livesIn some Environment) (pred. acc.: 50.00%,
F-measure: 66.67%)
6: Animal or (not (livesIn some Thing)) (pred. acc.: 50.00%, F-measure:
66.67%)
7: Animal and (Environment or (livesIn some Environment)) (pred. acc.:
50.00%, F-measure: 66.67%)
8: (not (livesIn some Thing)) or (livesIn some Environment) (pred. acc.:
50.00%, F-measure: 66.67%)
9: Animal or (Environment and (not (livesIn some Thing))) (pred. acc.:
50.00%, F-measure: 66.67%)
10: Animal or Environment or (not (livesIn some Thing)) (pred. acc.:
50.00%, F-measure: 66.67%)
As you can see it never gets to use the hasValue constructor. For the
configuration file, I have used:
prefixes = [ ("ex”,”prefix#”) ]
ks.type = "OWL File"
ks.fileName = "toyLearner.owl"
reasoner.type = "fast instance checker"
reasoner.sources = {ks}
lp.reasoner = reasoner
lp.type = "posNegStandard"
lp.positiveExamples = {"ex:Cat"}
lp.negativeExamples = {"ex:Fish"}
op.type = "rho"
op.useNegation = false
op.useCardinalityRestrictions = false
op.useHasValueConstructor = true
alg.type = "celoe"
alg.maxExecutionTimeInSeconds = 60
alg.noisePercentage = 0.0
alg.reasoner = reasoner
Additionally on more complex ontologies, the algorithm does not seem to
search for too specific expressions, meaning that instead of
specializing a expression (trough conjunctions) it always prefers to
make disjunctions. I suppose this part has to do with the breadth search
preferences (which is maybe preventing it from using the HasValue
constructor as well?), but I didn’t find how to set this parameter.
I have looked into the online documentation, and in the sample files you
provide but I could not get further.
If you could point out where should I change the file, or where to look
on how to properly set the parameters for using HasValue and controlling
the depth/breadth of the search, I would appreciate it.
Finally, many of the expressions use “ConceptA or ConceptB” as an
answer. Since only one part of the disjunction has to be true, if the
other part covers no examples at all, the algorithm still considers it
in the possible answer (eg. Animal or Environment, since Environment
covers 0% of the samples, I would like this concept to be excluded from
the answers provided, i.e. is trivial compared to answer 2. Animal). Is
there a way to control this behavior?
Thanks in advance,
Luis
|
|
From: Simon B. <sb...@in...> - 2017-03-31 09:36:32
|
Hi, DL-Learner is a complex project with many dependencies, what is your problem with downloading the dllearner-1.3.0.zip from https://github.co m/AKSW/DL-Learner/releases ? It contains all the required JAR files for DL-Learner. Take care, Simon On Fri, 2017-03-31 at 14:14 +0800, 沙磊 wrote: > Dear all: > > > > I am now working on a project in which DL-learner is required. However, I found that it is very difficult to download the jar file from https://github.com/AKSW/DL-Learner/releases. So can anyone directly send me an execuable jar? Thank you very much! > > > > > Lei Sha > Peking University > ------------------------------------------------------------------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, Slashdot.org! http://sdm.link/slashdot > _______________________________________________ > dl-learner-discussion mailing list > dl-...@li... > https://lists.sourceforge.net/lists/listinfo/dl-learner-discussion |
|
From: Simon B. <sb...@in...> - 2017-03-31 08:34:11
|
Hi Sarker, Thanks for bringing this issue to our attention. The website contains incorrect or outdated information and we will correct this soon. In the meantime, please refer to the following Maven repositories: <repositories> <repository> <releases /> <id>maven.aksw.internal</id> <name>University Leipzig, AKSW Maven2 Repository</name> <url>http://maven.aksw.org/repository/internal</url>; </repository> <repository> <snapshots /> <id>maven.aksw.snapshots</id> <name>University Leipzig, AKSW Maven2 Repository</name> <url>http://maven.aksw.org/repository/snapshots</url>; </repository> And <dependencies> <dependency> <groupId>org.dllearner</groupId> <artifactId>interfaces</artifactId> <version>1.3.0</version> Maven Archiva Website: http://maven.aksw.org/archiva/#artifact~internal/org.dllearner/interfaces DL-Learner is not included in Maven Central. Best wishes, On Fri, 2017-03-31 at 05:35 +0000, Sarker, Md Kamruzzaman wrote: > Dear Concern, > With due respect I am trying to use DL-Learner as maven dependency in my java program. > > I am following the instructions given in https://dl-learner.org/development/maven/<https://urldefense.proofpoint.com/v2/url?u=https-3A__dl-2Dlearner.org_development_maven_&d=DwMFAw&c=3buyMx9JlH1z22L_G5pM28wz_Ru6WjhVHwo-vpeS0Gk&r=gOKJ7GGIYSN5ZikR0Wci79-a9BTFdST29ynNAKTmkas&m=awBJOF1uiNJAXKLqh3Qp5yTGKx_VqcwtU4GtLQ2gg3I&s=Ctxbe_v8lnEYUkE9VmPpTcypty9BYGOKXITr5_Min9M&e=>; but the existing version number, i am not getting. > > [cid:787e0336-4aa2-4d49-9049-d2cbf2a83709] > > > When I am searching in maven central repository (http://search.maven.org/<https://urldefense.proofpoint.com/v2/url?u=http-3A__search.maven.org_&d=DwMFAw&c=3buyMx9JlH1z22L_G5pM28wz_Ru6WjhVHwo-vpeS0Gk&r=gOKJ7GGIYSN5ZikR0Wci79-a9BTFdST29ynNAKTmkas&m=awBJOF1uiNJAXKLqh3Qp5yTGKx_VqcwtU4GtLQ2gg3I&s=32xKtDMYVFTsRJjE3qKIXxi7L7qE5LgpBagLa4a86uA&e=>;) dl-learner is also not found. > > Would you please let me know how can I use DL-Learner as maven dependency? > > With Regards, > ------------- > Md Kamruzzaman Sarker > PhD Student > Dept. of Computer Science and Engineering, Wright State University, Dayton, OH > http://dase.cs.wright.edu/people/kamruzzaman-sarker > > <http://dase.cs.wright.edu/people/kamruzzaman-sarker> > ------------------------------------------------------------------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, Slashdot.org! http://sdm.link/slashdot > _______________________________________________ > dl-learner-discussion mailing list > dl-...@li... > https://lists.sourceforge.net/lists/listinfo/dl-learner-discussion |
|
From: 沙磊 <130...@pk...> - 2017-03-31 06:14:50
|
Dear all: I am now working on a project in which DL-learner is required. However, I found that it is very difficult to download the jar file from https://github.com/AKSW/DL-Learner/releases. So can anyone directly send me an execuable jar? Thank you very much! Lei Sha Peking University |
|
From: Sarker, Md K. <sar...@wr...> - 2017-03-31 05:31:33
|
Dear Concern, With due respect I am trying to use DL-Learner as maven dependency in my java program. I am following the instructions given in https://dl-learner.org/development/maven/ but the existing version number, i am not getting. [cid:787e0336-4aa2-4d49-9049-d2cbf2a83709] When I am searching in maven central repository (http://search.maven.org/) dl-learner is also not found. Would you please let me know how can I use DL-Learner as maven dependency? With Regards, ------------- Md Kamruzzaman Sarker PhD Student Dept. of Computer Science and Engineering, Wright State University, Dayton, OH http://dase.cs.wright.edu/people/kamruzzaman-sarker |
|
From: Simon B. <sb...@in...> - 2017-03-20 08:12:14
|
Dear Md Kamruzzaman Sarker, On Mon, 2017-03-20 at 01:30 +0000, Sarker, Md Kamruzzaman wrote: > AbstractCELA la; > > la = new CELOE(lp, rc); > > ((CELOE) la).setStartClass(df.getOWLThing()); here, you need to call la.init(); > la.start(); All our objects require .init(). We are looking to enforce this code- wise in the future but for now please keep this in mind. Good luck. -- Simon Bin AKSW Group Universität Leipzig http://aksw.org/SimonBin tel:+49-341 97 32253 |
|
From: Sarker, Md K. <sar...@wr...> - 2017-03-20 02:06:03
|
Dear concern, With due respect, I am using DL-Learner jars as library in my java program. When I am executing: learningAlgorithm.start() function I am getting this error: Exception in thread "main" java.lang.ClassCastException: org.dllearner.algorithms.celoe.OENode cannot be cast to java.lang.Comparable at java.util.TreeMap.compare(TreeMap.java:1294) at java.util.TreeMap.put(TreeMap.java:538) at java.util.TreeSet.add(TreeSet.java:255) at org.dllearner.utilities.datastructures.AbstractSearchTree.notifyNode(AbstractSearchTree.java:65) at org.dllearner.core.AbstractSearchTreeNode.notifyTree(AbstractSearchTreeNode.java:81) at org.dllearner.core.AbstractSearchTreeNode.notifyTree(AbstractSearchTreeNode.java:76) at org.dllearner.utilities.datastructures.AbstractSearchTree.setRoot(AbstractSearchTree.java:87) at org.dllearner.utilities.datastructures.AbstractSearchTree.addNode(AbstractSearchTree.java:52) at org.dllearner.algorithms.celoe.CELOE.addNode(CELOE.java:549) at org.dllearner.algorithms.celoe.CELOE.start(CELOE.java:327) Source code for my simple program is: KnowledgeSource ks = new OWLAPIOntology(ontology); ks.init(); OWLAPIReasoner baseReasoner = new OWLAPIReasoner(ks); baseReasoner.setReasonerImplementation(ReasonerImplementation.PELLET); baseReasoner.init(); ClosedWorldReasoner rc = new ClosedWorldReasoner(ks); rc.init(); PosOnlyLP lp = new PosOnlyLP(rc); lp.setPositiveExamples(posExamples); lp.init(); AbstractCELA la; la = new CELOE(lp, rc); ((CELOE) la).setStartClass(df.getOWLThing()); la.start(); Would you please help to give a hint how can I solve the problem? With Regards, ------------- Md Kamruzzaman Sarker PhD Student Dept. of Computer Science and Engineering, Wright State University, Dayton, OH http://dase.cs.wright.edu/people/kamruzzaman-sarker |
|
From: Faranak S. <f.s...@qm...> - 2017-03-13 10:46:57
|
Dear Simon, Sorry to be a bother! Thanks a lot. Best, Faranak -- Faranak Sobhani PhD Electronic Engineering Student MMV (Multimedia and Vision) Lab School of Electronic Engineering and Computer Science Queen Mary University of London Mile End Road, London E1 4NS, UK ________________________________ From: Simon Bin <sb...@in...> Sent: 13 March 2017 10:37 To: Faranak Sobhani; dl-...@li... Subject: Re: Fwd: Re: Dl-Learner Dear Faranak please send further Replies to <dl-...@li...> (use Reply All or Reply to List button in your Mail program) It does not make any sense that you send the same email to 4 People and receive 4 independent replies. Thanks, On Mon, 2017-03-13 at 09:53 +0000, Faranak Sobhani wrote: > Dear Simon, > > Thank you very much for getting beck to me. > > > The reason I can not share the ontology is, it is part of the project and I am somehow using that for my research as well. This is the only reason as this version hasn't publish yet. > > > What I mean exactly is the result I'm getting from protege is different with what I get from code and by coding I just get results which is not that much helpful for me. > > To make it more clear in the following example I did use the same (.owl ) file and the first solution is what I got from source code(.java) and the second one from protege. > > > From Code; > > solutions: > 1: isFrom only SpatioTemporalParticular 54.24% > 2: isFrom only Particular 54.24% > 3: Thing 50.85% > 4: Stative 50.85% > 5: SpatioTemporalParticular 50.85% > 6: PhysicalAggression 50.85% > 7: Perdurant 50.85% > 8: Particular 50.85% > 9: GlobalPerdurant 50.85% > 10: Activities 50.85% > 11: ActivePhysicalAggresion 50.85% > 12: isFrom some Thing 50.85% > 13: Particular or TimeDifference 50.85% > 14: GlobalPerdurant or TimeDifference 50.85% > 15: GlobalPerdurant or Particular 50.85% > 16: DistanceToAParticular or Particular 50.85% > 17: DistanceToAParticular or GlobalPerdurant 50.85% > > > > From Protege ; > [cid:06f8e3a3-930e-48c0-8075-bb00b55572da] > > > As you can see by protege more properties involved and for some unknown reason I'm not able to get the relation when I run the java code. > Is there any specific setting I need to change in the code or any suggestion that I can have the properties involved? > > > > I am using positive example only, I mean considering only the instances of the target class. In other words, I do have a Target class and all related instance for that class and based on these instances I'm trying to learn the definition of the class. > > > If my explanation is still not clear that you can somehow help me based on them, as you did suggest I will create some example data and share the JAVA Code Example. > > > Appreciate you consideration and help. > > > -- > Faranak Sobhani > PhD Electronic Engineering Student > MMV (Multimedia and Vision) Lab > School of Electronic Engineering and Computer Science > Queen Mary University of London > Mile End Road, London E1 4NS, UK > > > > ________________________________ > From: Simon Bin <sb...@in...> > Sent: 13 March 2017 09:36 > To: Faranak Sobhani > Cc: Lorenz B.; Patrick Westphal > Subject: Re: Fwd: Re: Dl-Learner > > Dear Faranak, > > maybe you can at least share your JAVA Code Example with us? > > Since you cannot provide the ontology, can you tell us more about the > Classes and Properties in it? Is there a Class Hierarchy > (subClassOf...?) Can you describe the structure of the data? Maybe you > can create some fake example data for one or two instances? > > Are you using the DL-Learner with Positive and Negative examples or > Concept learning? You can also try to increase the > maxExecutionTimeInSeconds in case time would be the limiting factor. > > Cheers, > Simon > > > On Mon, 2017-03-13 at 09:55 +0100, Lorenz B. wrote: > > > > > > -------- Forwarded Message -------- > > Subject: Re: Dl-Learner > > Date: Fri, 10 Mar 2017 12:46:22 +0000 > > From: Faranak Sobhani <f.s...@qm...> > > To: Lorenz B. <bue...@in...> > > > > > > > > Dear Professor, > > > > Sorry for disturbing again. > > I got stuck in some experiments with DL-Learner and can not proceed. > > > > Firstly I did try with Protege DL plugin out of 7 concepts, for 4 > > concepts I got the really good results (solution) but then when I did > > use the source code(CELOE.java) to check whether I would be able to have > > solutions for the other 3Concepts- I faced with the problem that for > > every concept I can get the solution like following; > > > > > > solutions: > > 1: Stative 85.96% > > 2: Activities 85.96% > > 3: Thing 19.30% > > 4: SpatioTemporalParticular 19.30% > > 5: Perdurant 19.30% > > 6: Particular 19.30% > > 7: GlobalPerdurant 19.30% > > 8: Event 19.30% > > > > > > > > I did try the code with several provide (.owl) examples. For all of > > them, it works and I can get resealable solutions such as following. > > > > solutions: > > 1: getsRingReplacedAtPosition some Thing 100.00% > > 2: (getsReplacedBy some Substituent) and (getsRingReplacedAtPosition > > some Thing) 100.00% > > 3: (Drug or Substituent) and (getsReplacedBy some Substituent) 100.00% > > 4: (Drug or Size) and (getsReplacedBy some Substituent) 100.00% > > 5: (Drug or Sigma) and (getsReplacedBy some Substituent) 100.00% > > 6: (Drug or Polar) and (getsReplacedBy some Substituent) 100.00% > > 7: (Drug or PiDonor) and (getsReplacedBy some Substituent) 100.00% > > 8: (Drug or PiAcceptor) and (getsReplacedBy some Substituent) 100.00% > > 9: (Drug or HDonor) and (getsReplacedBy some Substituent) 100.00% > > > > I went through code several times and it is really not clear for me how > > I can fix this problem, I did try to debug line by line -seems like > > there is a secret solution for that that I can not get it really. > > > > > > I was wondering if there is any limitation in terms of a number of > > concept or object hierarchy? As when I am trying each concept > > individually in a separate .owl file I can have good solutions, but when > > I add them to my ontology with the following metric I can't get any > > solutions. > > > > > > Following is my ontology metrics; > > Axiom9999 > > Logical axiom count7375 > > Declaration axioms count2453 > > Class count482 > > Object property count148 > > Data property count55 > > Individual count1763 > > > > Any chance you can help me with this problem PLEASE? > > > > Your support would be greatly appreciated. > > > > Best, > > Faranak > > > > > > -- > > *Faranak Sobhani* > > PhD Electronic Engineering Student > > *MMV (Multimedia and Vision) Lab* > > School of Electronic Engineering and Computer Science > > Queen Mary University of London > > Mile End Road, London E1 4NS, UK > > > > > > > > ------------------------------------------------------------------------ > > *From:* Lorenz B. <bue...@in...> > > *Sent:* 15 February 2017 11:12 > > *To:* Faranak Sobhani > > *Subject:* Re: Dl-Learner > > > > Hello Faranak, > > > > can you share the ontology with us and maybe also give us a descriptions > > of the steps you did? > > > > > > > > Cheers, > > Lorenz > > > > > Dear Professor, > > > > > > Sorry to be a bother as, I said previously, I'm working on ontology > > > learning and currently focusing on DL-learner. > > > I came across few issues that I would be grateful if you could help me > > > over them *PLEASE*. > > > > > > I am using protege 5.1 with the latest available version of the > > > DL-Learner, for some unknown reason each time I run the reasoner and > > > selecting the suggestion for equivalence class ( I choose EL profile > > > from the setting section ) for the same concept I get different > > > hypothesis without even changing the setting. > > > More importantly, for most of my main concept(which I want to focus > > > on them more) I have the following error which is not really clear > > > for me > > > > > > * Level: ERROR Time: 1487097022334 Message: An error was thrown: > > > CELOE could not find any node with lesser accuracy. > > > java.lang.RuntimeException StackTrace: > > > org.dllearner.algorithms.celoe.CELOE.getNextNodeToExpand(CELOE.java:484) > > > org.dllearner.algorithms.celoe.CELOE.start(CELOE.java:333) > > > org.dllearner.tools.protege.Manager.startLearning(Manager.java:320) > > > org.dllearner.tools.protege.ActionHandler$SuggestionRetriever.doInBackground(ActionHandler.java:240) > > > org.dllearner.tools.protege.ActionHandler$SuggestionRetriever.doInBackground(ActionHandler.java:184) > > > javax.swing.SwingWorker$1.call(SwingWorker.java:295) > > > java.util.concurrent.FutureTask.run(FutureTask.java:266) > > > javax.swing.SwingWorker.run(SwingWorker.java:334) > > > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) > > > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) > > > java.lang.Thread.run(Thread.java:745) > > > * > > > > > > Your support would be greatly appreciated. > > > Best, > > > Faranak > > > > > > > > > -- > > > *Faranak Sobhani* > > > PhD Electronic Engineering Student > > > *MMV (Multimedia and Vision) Lab* > > > School of Electronic Engineering and Computer Science > > > Queen Mary University of London > > > Mile End Road, London E1 4NS, UK > > > > > > > > > > > > ------------------------------------------------------------------------ > > > *From:* Lorenz B. <bue...@in...> > > > *Sent:* 02 November 2016 08:46 > > > *To:* Faranak Sobhani > > > *Subject:* Re: Dl-Learner > > > > > > Hello Faranak, > > > > > > from the exceptions it looks like you have multiple version of the > > > plugin installed. Can you please remove all DL-Learner libs first? If > > > you use Windows, I don't know which folders you have to cleanup. > > > > > > > > > And please don't use Protege 5.0 beta anymore. There is already 5.1.0 > > > released. > > > > > > > > > > > > > > > Kind regards, > > > Lorenz > > > > > > > Hi, > > > > > > > > Yes , I did place it in the Plugin folder. > > > > > > > > > > > > The first attache(DownloadPlugin.txt) is when I download Plugin and > > > > the second on is when I want to add it from File in > > > > protege(AddFromProtege.txt) > > > > > > > > > > > > Best, > > > > > > > > Faranak > > > > > > > > > > > > > > > > -- > > > > *Faranak Sobhani* > > > > PhD Electronic Engineering Student > > > > *MMV (Multimedia and Vision) Lab* > > > > School of Electronic Engineering and Computer Science > > > > Queen Mary University of London > > > > Mile End Road, London E1 4NS, UK > > > > > > > > > > > > > > > > ------------------------------------------------------------------------ > > > > *From:* Lorenz B. <bue...@in...> > > > > *Sent:* 01 November 2016 11:25 > > > > *To:* Faranak Sobhani > > > > *Subject:* Re: Dl-Learner > > > > > > > > Hello Faranak, > > > > > > > > where did you put the JAR file? It has to be in the 'plugins' folder. > > > > Can you attach the log messages from the start of Protege? This > > > > should show every working plugin. And also error messages. > > > > > > > > > > > > > > > > Kind regards, > > > > Lorenz > > > > > > > > > Thank you very much for getting back to me. > > > > > > > > > > > > > > > I have used the attached Plugin both for protege 4.3 and 5 and I did > > > > > the steps as it is mentioned in read me! But after choosing the > > > > > class in the class hierarchy view and selecting the equivalence tab, > > > > > can't see the DL-Learner tab . I just have the same 4 tabs as I had > > > > > previously ( Object restriction, Data restriction, Class hierarchy > > > > > and class expression editor). > > > > > > > > > > > > > > > Can you please kindly help me over that . ( Where do you see the > > > > > problem? ) > > > > > > > > > > > > > > > Would be really kind of you if sending me the protege version which > > > > > works for you, although I have used both 4.3 and 5 downloaded from > > > > > the protege site ! > > > > > > > > > > > > > > > Best, > > > > > > > > > > Faranak > > > > > > > > > > > > > > > -- > > > > > *Faranak Sobhani* > > > > > PhD Electronic Engineering Student > > > > > *MMV (Multimedia and Vision) Lab* > > > > > School of Electronic Engineering and Computer Science > > > > > Queen Mary University of London > > > > > Mile End Road, London E1 4NS, UK > > > > > > > > > > > > > > > > > > > > ------------------------------------------------------------------------ > > > > > *From:* Lorenz B. <bue...@in...> > > > > > *Sent:* 28 October 2016 12:46 > > > > > *To:* Faranak Sobhani > > > > > *Cc:* Jens Lehmann > > > > > *Subject:* Re: Dl-Learner > > > > > > > > > > Dear Farank, > > > > > > > > > > not sure why it did not work for you, but we created a new > > > > > pre-release right now [1]. This worked for me with latest Protege > > > > > 5.1.0. Let us know if something does not work. > > > > > > > > > > Note, that we also updated the README such that you can find the > > > > > DL-Learner tab easier. Probably the previous documentation was a bit > > > > > misleading as the DL-Learner plugin is just a tab in a specific view > > > > > and not a proper Protege tab like other plugins provide. > > > > > > > > > > We will also try to make the plugin available via the Protege plugin > > > > > library feature, but this might take some time as we have to contact > > > > > the maintainer first. > > > > > > > > > > > > > > > [1] > > > > > https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1 [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> github.com DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; > > AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > > > > > > > > > > > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> github.com DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; > > AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > > > > > > > > > > > AKSW/DL-Learner-Protege-Plugin > > > > > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> github.com DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; > > AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > > > > > > github.com > > > > > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner > > > > > framework > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > Kind regards, > > > > > Lorenz > > > > > > > > > > > > > > > > > -------- Ursprüngliche Nachricht -------- > > > > > > Von: Faranak Sobhani <f.s...@qm...> > > > > > > Datum: 27.10.16 21:21 (GMT+01:00) > > > > > > An: jen...@cs... > > > > > > Betreff: Dl-Learner > > > > > > > > > > > > Dear Professor, > > > > > > > > > > > > I am a PhD student working on Knowledge representation. > > > > > > > > > > > > I am trying to use Dl-Learner-Protege-Plugin, But for some unknown > > > > > > reason I am not able to work with that. > > > > > > > > > > > > > > > > > > Basically, I did try both operations; Downloading the plugin from > > > > > > the "http://dl-learner.org/community/protege-plugin/" and also use > > Protégé Plugin<http://dl-learner.org/community/protege-plugin/> Protégé Plugin<http://dl-learner.org/community/protege-plugin/> dl-learner.org Protégé DL-Learner Plugin. The Protégé 4 DL-Learner plugin allows to learn equivalence and super class axioms based on the instance data in the ontologies loaded ... > dl-learner.org > Protégé DL-Learner Plugin. The Protégé 4 DL-Learner plugin allows to learn equivalence and super class axioms based on the instance data in the ontologies loaded ... > > > > > > > > > from the “File“ => “Preferences“ => “Plugins“. > > > > > > > > > > > > > > > > > > I used the download file both for protege 4.3 and 5. However, can > > > > > > not have the Dl-learner tab. Also, from the second option, when I > > > > > > use the protege 4.3 "checking for downloads" tab, it tells me > > > > > > there is no update and when I use from protege 5, I can see the > > > > > > DL-Learner version 8 , but after installing it gives me an error of > > > > > > " some error found downloading plugin" > > > > > > > > > > > > > > > > > > Can you please kindly help me over that. > > > > > > > > > > > > > > > > > > Best, > > > > > > > > > > > > Faranak > > > > > > > > > > > > > > > > > > > > > > > > -- > > > > > > *Faranak Sobhani* > > > > > > PhD Electronic Engineering Student > > > > > > *MMV (Multimedia and Vision) Lab* > > > > > > School of Electronic Engineering and Computer Science > > > > > > Queen Mary University of London > > > > > > Mile End Road, London E1 4NS, UK > > > > > > > > > > > > > > > > -- > > > > > Lorenz Bühmann > > > > > AKSW group, University of Leipzig > > > > > Group: http://aksw.org - semantic web research center Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> aksw.org The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> aksw.org The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > > > > > > > > > > -- > > > > Lorenz Bühmann > > > > AKSW group, University of Leipzig > > > > Group: http://aksw.org - semantic web research center Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> aksw.org The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> aksw.org The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > > > > > > > > -- > > > Lorenz Bühmann > > > AKSW group, University of Leipzig > > > Group: http://aksw.org - semantic web research center Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> aksw.org The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> aksw.org The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > > > > > > |
|
From: Simon B. <sb...@in...> - 2017-03-13 10:37:52
|
Dear Faranak please send further Replies to <dl-...@li...> (use Reply All or Reply to List button in your Mail program) It does not make any sense that you send the same email to 4 People and receive 4 independent replies. Thanks, On Mon, 2017-03-13 at 09:53 +0000, Faranak Sobhani wrote: > Dear Simon, > > Thank you very much for getting beck to me. > > > The reason I can not share the ontology is, it is part of the project and I am somehow using that for my research as well. This is the only reason as this version hasn't publish yet. > > > What I mean exactly is the result I'm getting from protege is different with what I get from code and by coding I just get results which is not that much helpful for me. > > To make it more clear in the following example I did use the same (.owl ) file and the first solution is what I got from source code(.java) and the second one from protege. > > > From Code; > > solutions: > 1: isFrom only SpatioTemporalParticular 54.24% > 2: isFrom only Particular 54.24% > 3: Thing 50.85% > 4: Stative 50.85% > 5: SpatioTemporalParticular 50.85% > 6: PhysicalAggression 50.85% > 7: Perdurant 50.85% > 8: Particular 50.85% > 9: GlobalPerdurant 50.85% > 10: Activities 50.85% > 11: ActivePhysicalAggresion 50.85% > 12: isFrom some Thing 50.85% > 13: Particular or TimeDifference 50.85% > 14: GlobalPerdurant or TimeDifference 50.85% > 15: GlobalPerdurant or Particular 50.85% > 16: DistanceToAParticular or Particular 50.85% > 17: DistanceToAParticular or GlobalPerdurant 50.85% > > > > From Protege ; > [cid:06f8e3a3-930e-48c0-8075-bb00b55572da] > > > As you can see by protege more properties involved and for some unknown reason I'm not able to get the relation when I run the java code. > Is there any specific setting I need to change in the code or any suggestion that I can have the properties involved? > > > > I am using positive example only, I mean considering only the instances of the target class. In other words, I do have a Target class and all related instance for that class and based on these instances I'm trying to learn the definition of the class. > > > If my explanation is still not clear that you can somehow help me based on them, as you did suggest I will create some example data and share the JAVA Code Example. > > > Appreciate you consideration and help. > > > -- > Faranak Sobhani > PhD Electronic Engineering Student > MMV (Multimedia and Vision) Lab > School of Electronic Engineering and Computer Science > Queen Mary University of London > Mile End Road, London E1 4NS, UK > > > > ________________________________ > From: Simon Bin <sb...@in...> > Sent: 13 March 2017 09:36 > To: Faranak Sobhani > Cc: Lorenz B.; Patrick Westphal > Subject: Re: Fwd: Re: Dl-Learner > > Dear Faranak, > > maybe you can at least share your JAVA Code Example with us? > > Since you cannot provide the ontology, can you tell us more about the > Classes and Properties in it? Is there a Class Hierarchy > (subClassOf...?) Can you describe the structure of the data? Maybe you > can create some fake example data for one or two instances? > > Are you using the DL-Learner with Positive and Negative examples or > Concept learning? You can also try to increase the > maxExecutionTimeInSeconds in case time would be the limiting factor. > > Cheers, > Simon > > > On Mon, 2017-03-13 at 09:55 +0100, Lorenz B. wrote: > > > > > > -------- Forwarded Message -------- > > Subject: Re: Dl-Learner > > Date: Fri, 10 Mar 2017 12:46:22 +0000 > > From: Faranak Sobhani <f.s...@qm...> > > To: Lorenz B. <bue...@in...> > > > > > > > > Dear Professor, > > > > Sorry for disturbing again. > > I got stuck in some experiments with DL-Learner and can not proceed. > > > > Firstly I did try with Protege DL plugin out of 7 concepts, for 4 > > concepts I got the really good results (solution) but then when I did > > use the source code(CELOE.java) to check whether I would be able to have > > solutions for the other 3Concepts- I faced with the problem that for > > every concept I can get the solution like following; > > > > > > solutions: > > 1: Stative 85.96% > > 2: Activities 85.96% > > 3: Thing 19.30% > > 4: SpatioTemporalParticular 19.30% > > 5: Perdurant 19.30% > > 6: Particular 19.30% > > 7: GlobalPerdurant 19.30% > > 8: Event 19.30% > > > > > > > > I did try the code with several provide (.owl) examples. For all of > > them, it works and I can get resealable solutions such as following. > > > > solutions: > > 1: getsRingReplacedAtPosition some Thing 100.00% > > 2: (getsReplacedBy some Substituent) and (getsRingReplacedAtPosition > > some Thing) 100.00% > > 3: (Drug or Substituent) and (getsReplacedBy some Substituent) 100.00% > > 4: (Drug or Size) and (getsReplacedBy some Substituent) 100.00% > > 5: (Drug or Sigma) and (getsReplacedBy some Substituent) 100.00% > > 6: (Drug or Polar) and (getsReplacedBy some Substituent) 100.00% > > 7: (Drug or PiDonor) and (getsReplacedBy some Substituent) 100.00% > > 8: (Drug or PiAcceptor) and (getsReplacedBy some Substituent) 100.00% > > 9: (Drug or HDonor) and (getsReplacedBy some Substituent) 100.00% > > > > I went through code several times and it is really not clear for me how > > I can fix this problem, I did try to debug line by line -seems like > > there is a secret solution for that that I can not get it really. > > > > > > I was wondering if there is any limitation in terms of a number of > > concept or object hierarchy? As when I am trying each concept > > individually in a separate .owl file I can have good solutions, but when > > I add them to my ontology with the following metric I can't get any > > solutions. > > > > > > Following is my ontology metrics; > > Axiom9999 > > Logical axiom count7375 > > Declaration axioms count2453 > > Class count482 > > Object property count148 > > Data property count55 > > Individual count1763 > > > > Any chance you can help me with this problem PLEASE? > > > > Your support would be greatly appreciated. > > > > Best, > > Faranak > > > > > > -- > > *Faranak Sobhani* > > PhD Electronic Engineering Student > > *MMV (Multimedia and Vision) Lab* > > School of Electronic Engineering and Computer Science > > Queen Mary University of London > > Mile End Road, London E1 4NS, UK > > > > > > > > ------------------------------------------------------------------------ > > *From:* Lorenz B. <bue...@in...> > > *Sent:* 15 February 2017 11:12 > > *To:* Faranak Sobhani > > *Subject:* Re: Dl-Learner > > > > Hello Faranak, > > > > can you share the ontology with us and maybe also give us a descriptions > > of the steps you did? > > > > > > > > Cheers, > > Lorenz > > > > > Dear Professor, > > > > > > Sorry to be a bother as, I said previously, I'm working on ontology > > > learning and currently focusing on DL-learner. > > > I came across few issues that I would be grateful if you could help me > > > over them *PLEASE*. > > > > > > I am using protege 5.1 with the latest available version of the > > > DL-Learner, for some unknown reason each time I run the reasoner and > > > selecting the suggestion for equivalence class ( I choose EL profile > > > from the setting section ) for the same concept I get different > > > hypothesis without even changing the setting. > > > More importantly, for most of my main concept(which I want to focus > > > on them more) I have the following error which is not really clear > > > for me > > > > > > * Level: ERROR Time: 1487097022334 Message: An error was thrown: > > > CELOE could not find any node with lesser accuracy. > > > java.lang.RuntimeException StackTrace: > > > org.dllearner.algorithms.celoe.CELOE.getNextNodeToExpand(CELOE.java:484) > > > org.dllearner.algorithms.celoe.CELOE.start(CELOE.java:333) > > > org.dllearner.tools.protege.Manager.startLearning(Manager.java:320) > > > org.dllearner.tools.protege.ActionHandler$SuggestionRetriever.doInBackground(ActionHandler.java:240) > > > org.dllearner.tools.protege.ActionHandler$SuggestionRetriever.doInBackground(ActionHandler.java:184) > > > javax.swing.SwingWorker$1.call(SwingWorker.java:295) > > > java.util.concurrent.FutureTask.run(FutureTask.java:266) > > > javax.swing.SwingWorker.run(SwingWorker.java:334) > > > java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) > > > java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) > > > java.lang.Thread.run(Thread.java:745) > > > * > > > > > > Your support would be greatly appreciated. > > > Best, > > > Faranak > > > > > > > > > -- > > > *Faranak Sobhani* > > > PhD Electronic Engineering Student > > > *MMV (Multimedia and Vision) Lab* > > > School of Electronic Engineering and Computer Science > > > Queen Mary University of London > > > Mile End Road, London E1 4NS, UK > > > > > > > > > > > > ------------------------------------------------------------------------ > > > *From:* Lorenz B. <bue...@in...> > > > *Sent:* 02 November 2016 08:46 > > > *To:* Faranak Sobhani > > > *Subject:* Re: Dl-Learner > > > > > > Hello Faranak, > > > > > > from the exceptions it looks like you have multiple version of the > > > plugin installed. Can you please remove all DL-Learner libs first? If > > > you use Windows, I don't know which folders you have to cleanup. > > > > > > > > > And please don't use Protege 5.0 beta anymore. There is already 5.1.0 > > > released. > > > > > > > > > > > > > > > Kind regards, > > > Lorenz > > > > > > > Hi, > > > > > > > > Yes , I did place it in the Plugin folder. > > > > > > > > > > > > The first attache(DownloadPlugin.txt) is when I download Plugin and > > > > the second on is when I want to add it from File in > > > > protege(AddFromProtege.txt) > > > > > > > > > > > > Best, > > > > > > > > Faranak > > > > > > > > > > > > > > > > -- > > > > *Faranak Sobhani* > > > > PhD Electronic Engineering Student > > > > *MMV (Multimedia and Vision) Lab* > > > > School of Electronic Engineering and Computer Science > > > > Queen Mary University of London > > > > Mile End Road, London E1 4NS, UK > > > > > > > > > > > > > > > > ------------------------------------------------------------------------ > > > > *From:* Lorenz B. <bue...@in...> > > > > *Sent:* 01 November 2016 11:25 > > > > *To:* Faranak Sobhani > > > > *Subject:* Re: Dl-Learner > > > > > > > > Hello Faranak, > > > > > > > > where did you put the JAR file? It has to be in the 'plugins' folder. > > > > Can you attach the log messages from the start of Protege? This > > > > should show every working plugin. And also error messages. > > > > > > > > > > > > > > > > Kind regards, > > > > Lorenz > > > > > > > > > Thank you very much for getting back to me. > > > > > > > > > > > > > > > I have used the attached Plugin both for protege 4.3 and 5 and I did > > > > > the steps as it is mentioned in read me! But after choosing the > > > > > class in the class hierarchy view and selecting the equivalence tab, > > > > > can't see the DL-Learner tab . I just have the same 4 tabs as I had > > > > > previously ( Object restriction, Data restriction, Class hierarchy > > > > > and class expression editor). > > > > > > > > > > > > > > > Can you please kindly help me over that . ( Where do you see the > > > > > problem? ) > > > > > > > > > > > > > > > Would be really kind of you if sending me the protege version which > > > > > works for you, although I have used both 4.3 and 5 downloaded from > > > > > the protege site ! > > > > > > > > > > > > > > > Best, > > > > > > > > > > Faranak > > > > > > > > > > > > > > > -- > > > > > *Faranak Sobhani* > > > > > PhD Electronic Engineering Student > > > > > *MMV (Multimedia and Vision) Lab* > > > > > School of Electronic Engineering and Computer Science > > > > > Queen Mary University of London > > > > > Mile End Road, London E1 4NS, UK > > > > > > > > > > > > > > > > > > > > ------------------------------------------------------------------------ > > > > > *From:* Lorenz B. <bue...@in...> > > > > > *Sent:* 28 October 2016 12:46 > > > > > *To:* Faranak Sobhani > > > > > *Cc:* Jens Lehmann > > > > > *Subject:* Re: Dl-Learner > > > > > > > > > > Dear Farank, > > > > > > > > > > not sure why it did not work for you, but we created a new > > > > > pre-release right now [1]. This worked for me with latest Protege > > > > > 5.1.0. Let us know if something does not work. > > > > > > > > > > Note, that we also updated the README such that you can find the > > > > > DL-Learner tab easier. Probably the previous documentation was a bit > > > > > misleading as the DL-Learner plugin is just a tab in a specific view > > > > > and not a proper Protege tab like other plugins provide. > > > > > > > > > > We will also try to make the plugin available via the Protege plugin > > > > > library feature, but this might take some time as we have to contact > > > > > the maintainer first. > > > > > > > > > > > > > > > [1] > > > > > https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1 > > [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; > > AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > > > > > > > > > > > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > > [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; > > AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > > > > > > > > > > > AKSW/DL-Learner-Protege-Plugin > > > > > <https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > > [https://avatars1.githubusercontent.com/u/770163?v=3&s=400]<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1>; > > AKSW/DL-Learner-Protege-Plugin<https://github.com/AKSW/DL-Learner-Protege-Plugin/releases/tag/v0.9-rc1> > github.com > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner framework > > > > > > > > github.com > > > > > DL-Learner-Protege-Plugin - A Protégé plugin for the DL-Learner > > > > > framework > > > > > > > > > > > > > > > > > > > > > > > > > > > > > > Kind regards, > > > > > Lorenz > > > > > > > > > > > > > > > > > -------- Ursprüngliche Nachricht -------- > > > > > > Von: Faranak Sobhani <f.s...@qm...> > > > > > > Datum: 27.10.16 21:21 (GMT+01:00) > > > > > > An: jen...@cs... > > > > > > Betreff: Dl-Learner > > > > > > > > > > > > Dear Professor, > > > > > > > > > > > > I am a PhD student working on Knowledge representation. > > > > > > > > > > > > I am trying to use Dl-Learner-Protege-Plugin, But for some unknown > > > > > > reason I am not able to work with that. > > > > > > > > > > > > > > > > > > Basically, I did try both operations; Downloading the plugin from > > > > > > the "http://dl-learner.org/community/protege-plugin/" and also use > > Protégé Plugin<http://dl-learner.org/community/protege-plugin/> > dl-learner.org > Protégé DL-Learner Plugin. The Protégé 4 DL-Learner plugin allows to learn equivalence and super class axioms based on the instance data in the ontologies loaded ... > > > > > > > > > from the “File“ => “Preferences“ => “Plugins“. > > > > > > > > > > > > > > > > > > I used the download file both for protege 4.3 and 5. However, can > > > > > > not have the Dl-learner tab. Also, from the second option, when I > > > > > > use the protege 4.3 "checking for downloads" tab, it tells me > > > > > > there is no update and when I use from protege 5, I can see the > > > > > > DL-Learner version 8 , but after installing it gives me an error of > > > > > > " some error found downloading plugin" > > > > > > > > > > > > > > > > > > Can you please kindly help me over that. > > > > > > > > > > > > > > > > > > Best, > > > > > > > > > > > > Faranak > > > > > > > > > > > > > > > > > > > > > > > > -- > > > > > > *Faranak Sobhani* > > > > > > PhD Electronic Engineering Student > > > > > > *MMV (Multimedia and Vision) Lab* > > > > > > School of Electronic Engineering and Computer Science > > > > > > Queen Mary University of London > > > > > > Mile End Road, London E1 4NS, UK > > > > > > > > > > > > > > > > -- > > > > > Lorenz Bühmann > > > > > AKSW group, University of Leipzig > > > > > Group: http://aksw.org - semantic web research center > > Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > > > > > > > > > > -- > > > > Lorenz Bühmann > > > > AKSW group, University of Leipzig > > > > Group: http://aksw.org - semantic web research center > > Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > > > > > > > > -- > > > Lorenz Bühmann > > > AKSW group, University of Leipzig > > > Group: http://aksw.org - semantic web research center > > Agile Knowledge Engineering and Semantic Web (AKSW ...<http://aksw.org/> > aksw.org > The USPTO Linked Patent Dataset release (2017-02-24T17:18:51+01:00 by Mofeed Hassan) 2017-02-24T17:18:51+01:00 by Mofeed Hassan. Dear all, We are happy to announce ... > > > > > > > |
|
From: Jeremy T. <jer...@au...> - 2017-01-15 14:23:21
|
dear dl-learner gurus, i am searching for the simplest approach to create a question ansering system for a specific programming API. dl-learner looks like a pretty good candidate. howevver, as far as i can tell so far, it requires a pretty well-structured ontology as an input. i have a whole bunch of existing resources containing answers to all the questions the system should be able to handle: · API documentation · developer guideliness · discussion forum with tens of thousands of questions and answers · my blog with 1500+ quite extensive blog posts, many including Q&A sessions · stackoverflow q&a · email archives how would i go about creating an otology from that? can dl-learner somehow parse them automatically as they are? can i create some program to extract data from them and format it for dl-learner to use? i read about OWL and OWL-DL... that looks a bit scary at the moment... i am hoping for something easier. if need be, though, would definitely consider creating something in the format, if nothing easier is possible... here is a blog post listting my existing sources in more detail with exact link, in case that helps explain: http://thebuildingcoder.typepad.com/blog/2017/01/virtues-of-reproduction-research-mep-settings-ontology.html#8 thank you! cheers, jeremy |
|
From: Lorenz B. <spo...@st...> - 2017-01-11 10:35:09
|
Hello Soheil,
can please always use "reply to list" such that the discussion will be
continued on the mailing list?
regarding your problem, DL-Learner is a tool for (semi-)supervised
machine learning, thus, it needs for most cases some labeled data. In
the context of class expression learning, this usually means to provide
a set of positive examples ( here OWL individuals) which belong to the
class expression CE to learn, and optionally some negative examples
which must not belong to CE.
In the father example that you used as template you can see that a
learning problem has been defined as follows:
lp.type = "posNegStandard"
lp.positiveExamples = { "ex:stefan", "ex:markus", "ex:martin" }
lp.negativeExamples = { "ex:heinz", "ex:anna", "ex:michelle" }
This means we want to get a "good" description (aka OWL class
expression) of the individuals stefan, markus and martin based on their
instance data.
Moreover, we already decided that heinz, anna and michelle are
definitely different from the other by some extent and this should also
taken into account when learning the description.
You need to adapt this for your dataset and learning problem.
If you don't know what's contained in your data and don't have labeled
data, this is more typically a good use-case for unsupervised machine
learning. Prominent example algorithms here are, among others,
association rule mining or clustering.
Hope this helps.
Kind regards,
Lorenz
>
> Dear Lorenz,
>
> Thanks for your answer. My problem is how to write my config file. So,
> I as you said i change my config file (attached to this email) for my
> dataset (also attached) but it does't run.i created new Conference
> folder in examples and add my dataset in there.
>
> Thank you for your consideration in advance .
>
>
> Best Regards,
> Soheil
> ------------------------------------------------------------------------
> *From:* Lorenz B. <spo...@st...>
> *To:* dl-...@li...
> *Sent:* Saturday, December 17, 2016 3:17 PM
> *Subject:* Re: [DL-Learner discussion] Use N-Triple RDF dataset as an
> input for type recovery
>
> Hello Soheil,
>
> DL-Learner can be run either from CLI by using config files or from code.
> In your case, a config file has to be create which usually consists of
> (at least)
> * the dataset
> * the reasoner which is used to use inferred knowledge
> * the learning problem
> * the learning algorithm
>
> In any case, you have to define for what you want to learn an OWL
> class expression resp. OWL axiom. That means, you cannot simply copy
> and paste an exiting config file without redefining the dataset and
> the learning problem.
>
> I don't know where you found examples/sar, at least it's not contained
> in the latest release [1]. The dataset itself has to be defined like
> in the examples/father.conf file [2], i.e. if it is a file the path to
> the file has to be given
>
> ks.type = "OWL File"
> ks.fileName = "/PATH/TO/YOUR/FILE/dump_cleaned.nt"
>
> Feel free to ask further questions or even show us your config file
> and what you want/expect the DL-Learner to learn on this data.
>
>
>
>
>
>
>
>
>
>
> [1] https://github.com/AKSW/DL-Learner/tree/master/examples
> [2] https://github.com/AKSW/DL-Learner/blob/master/examples/father.conf
>
>
> Kind regards,
> Lorenz
>
>> Hello all,
>>
>> I would like to know how can I give my input as the n-triple dataset
>> for type recovery. I already installed the program and run it
>> perfectly. and run father.con example but I do not know how to run
>> another input files for examle there is the ntriple example in in the
>> example/sar but I do not know how to run dump_cleaned.nt . Does it
>> need to write config file for it. I would be grateful to provide some
>> helps for me, or if there is more detailed info (more than what it
>> is on the website). Thank you so much in advance for your
>> consideration and hope to hear from you soon.
>>
>> Best Regards
>>
>>
>> ------------------------------------------------------------------------------
>> Check out the vibrant tech community on one of the world's most
>> engaging tech sites, SlashDot.org! http://sdm.link/slashdot
>>
>>
>> _______________________________________________
>> dl-learner-discussion mailing list
>> dl-...@li...
>> <mailto:dl-...@li...>
>> https://lists.sourceforge.net/lists/listinfo/dl-learner-discussion
>
>
> ------------------------------------------------------------------------------
> Check out the vibrant tech community on one of the world's most
> engaging tech sites, SlashDot.org! http://sdm.link/slashdot
>
> _______________________________________________
> dl-learner-discussion mailing list
> dl-...@li...
> <mailto:dl-...@li...>
> https://lists.sourceforge.net/lists/listinfo/dl-learner-discussion
>
>
|
|
From: Lorenz B. <spo...@st...> - 2016-12-17 14:17:47
|
Hello Soheil, DL-Learner can be run either from CLI by using config files or from code. In your case, a config file has to be create which usually consists of (at least) * the dataset * the reasoner which is used to use inferred knowledge * the learning problem * the learning algorithm In any case, you have to define for what you want to learn an OWL class expression resp. OWL axiom. That means, you cannot simply copy and paste an exiting config file without redefining the dataset and the learning problem. I don't know where you found examples/sar, at least it's not contained in the latest release [1]. The dataset itself has to be defined like in the examples/father.conf file [2], i.e. if it is a file the path to the file has to be given ks.type = "OWL File" ks.fileName = "/PATH/TO/YOUR/FILE/dump_cleaned.nt" Feel free to ask further questions or even show us your config file and what you want/expect the DL-Learner to learn on this data. [1] https://github.com/AKSW/DL-Learner/tree/master/examples [2] https://github.com/AKSW/DL-Learner/blob/master/examples/father.conf Kind regards, Lorenz > Hello all, > > I would like to know how can I give my input as the n-triple dataset > for type recovery. I already installed the program and run it > perfectly. and run father.con example but I do not know how to run > another input files for examle there is the ntriple example in in the > example/sar but I do not know how to run dump_cleaned.nt . Does it > need to write config file for it. I would be grateful to provide some > helps for me, or if there is more detailed info (more than what it is > on the website). Thank you so much in advance for your consideration > and hope to hear from you soon. > > Best Regards > > > ------------------------------------------------------------------------------ > Check out the vibrant tech community on one of the world's most > engaging tech sites, SlashDot.org! http://sdm.link/slashdot > > > _______________________________________________ > dl-learner-discussion mailing list > dl-...@li... > https://lists.sourceforge.net/lists/listinfo/dl-learner-discussion |
|
From: Jens L. <le...@in...> - 2016-12-09 14:58:44
|
Dear all, the Smart Data Analytics group [1] is happy to announce SANSA 0.1 - the initial release of the Scalable Semantic Analytics Stack. SANSA combines distributed computing and semantic technologies in order to allow powerful machine learning, inference and querying capabilities for large knowledge graphs. * Website: http://sansa-stack.net * GitHub: https://github.com/SANSA-Stack * Download: http://sansa-stack.net/downloads-usage/ * ChangeLog: https://github.com/SANSA-Stack/SANSA-Stack/releases You can find the FAQ and usage examples at http://sansa-stack.net/faq/. The following features are currently supported by SANSA: * Support for reading and writing RDF files in N-Triples format * Support for reading OWL files in various standard formats * Querying and partitioning based on Sparqlify * Support for RDFS/RDFS Simple/OWL-Horst forward chaining inference * Initial RDF graph clustering support * Initial support for rule mining from RDF graphs We want to thank everyone who helped to create this release, in particular the projects Big Data Europe [2], HOBBIT [3] and SAKE [4]. View this announcement on Twitter and the SDA blog: http://sda.cs.uni-bonn.de/sansa-0-1/ https://twitter.com/SANSA_Stack/status/807231614086479872 Kind regards, The SANSA Development Team (http://sansa-stack.net/community/#Contributors) [1] http://sda.tech [2] http://www.big-data-europe.eu [3] https://project-hobbit.eu [4] https://www.sake-projekt.de/en/start/ -- Prof. Dr. Jens Lehmann http://jens-lehmann.org Computer Science Institute Knowledge Discovery Department University of Bonn Fraunhofer IAIS http://www.cs.uni-bonn.de http://www.iais.fraunhofer.de le...@un... jen...@ia... |
|
From: soheil r. <sr...@ya...> - 2016-12-02 11:30:44
|
Hello all, I would like to know how can I give my input as the n-triple dataset for type recovery. I already installed the program and run it perfectly. and run father.con example but I do not know how to run another input files for examle there is the ntriple example in in the example/sar but I do not know how to run dump_cleaned.nt . Does it need to write config file for it. I would be grateful to provide some helps for me, or if there is more detailed info (more than what it is on the website). Thank you so much in advance for your consideration and hope to hear from you soon. Best Regards |
|
From: Jens L. <le...@in...> - 2016-10-11 19:50:02
|
Dear all, the Smart Data Analytics group [1] is happy to announce DL-Learner 1.3. DL-Learner is a framework containing algorithms for supervised machine learning in RDF and OWL. DL-Learner can use various RDF and OWL serialization formats as well as SPARQL endpoints as input, can connect to most popular OWL reasoners and is easily and flexibly configurable. It extends concepts of Inductive Logic Programming and Relational Learning to the Semantic Web in order to allow powerful data analysis. Website: http://dl-learner.org GitHub page: https://github.com/AKSW/DL-Learner Download: https://github.com/AKSW/DL-Learner/releases ChangeLog: http://dl-learner.org/development/changelog/ DL-Learner is used for data analysis tasks within other tools such as ORE [2] and RDFUnit [3]. Technically, it uses refinement operator based, pattern-based and evolutionary techniques for learning on structured data. For a practical example, see [4]. DL-Learner also offers a plugin for Protégé [5], which can give suggestions for axioms to add. In the current release, we added a large number of new algorithms and features. For instance, DL-Learner supports terminological decision tree learning, it integrates the LEAP and EDGE systems as well as the BUNDLE probabilistic OWL reasoner. We migrated the system to Java 8, Jena 3, OWL API 4.2 and Spring 4.3. We want to point to some related efforts here: * A new DL-Learner overview article is available at [6]. * We started a benchmarking framework for supervised machine learning from structured data (not restricted to RDF/OWL) at [7]. * An article about the SPARQL reasoning component is now available at http://svn.aksw.org/papers/2016/ECAI_SPARQL_Learner/public.pdf . * An article about terminological decision tree learning is available at [8]. We want to thank everyone who helped to create this release, in particular we want to thank Giuseppe Cota who visited the core developer team and significantly improved DL-Learner. We also acknowledge support by the recently SAKE project [9], in which DL-Learner will be applied to event analysis in manufacturing use cases, as well as Big Data Europe [10] and HOBBIT [11] projects. View this announcement on Twitter and the AKSW blog: https://twitter.com/dllearner/status/785928687921299457 http://blog.aksw.org/dl-learner-1-3/ Kind regards, Lorenz Bühmann, Jens Lehmann, Patrick Westphal and Simon Bin [1] http://sda.tech [2] http://ore-tool.net [3] http://aksw.org/Projects/RDFUnit.html [4] http://dl-learner.org/community/carcinogenesis/ [5] https://github.com/AKSW/DL-Learner-Protege-Plugin [6] http://jens-lehmann.org/files/2016/jws_dllearner.pdf and http://www.sciencedirect.com/science/article/pii/S157082681630018X [7] https://github.com/AKSW/SML-Bench [8] http://dl-learner.org/Resources/Documents/ekaw_terminological_decision_trees.pdf [9] https://www.sake-projekt.de/en/start/ [10] http://www.big-data-europe.eu [11] https://project-hobbit.eu/ -- Prof. Dr. Jens Lehmann http://jens-lehmann.org Computer Science Institute Knowledge Discovery Department University of Bonn Fraunhofer IAIS http://www.cs.uni-bonn.de http://www.iais.fraunhofer.de le...@un... jen...@ia... |
|
From: Fabrizio R. <fab...@un...> - 2016-06-01 06:40:50
|
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
AI*IA Outgoing Mobility Grants 2016
Call for research visits
Deadline for applications: 10 June 2016
https://sites.google.com/a/aixia.it/italiano/premi/outgoing-mobility
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
To favour mobility of young researchers the Italian Association for
Artificial
Intelligence (AI*IA) issues the Association Outgoing Mobility Grants for
2015.
Applications are solicited for funding a research visit abroad of a PhD
student
enrolled at an Italian University.
Students will be funded by AI*IA which will cover their travel costs and
living
expenses (up to 2000 euro).
The funding will be provided as a reimbursement for the expenses incurred
in the
visit. After the visit, the awarded person should send the Association the
receipts of her/his costs for which she/he would like to be refunded.
The central aim of these extended visits is to build a research bridge
between
researchers and to create a solid basis for long term collaborations.
Moreover,
the visit has to lead to a submission of an article on a joint
research topics to the Intelligenza Artificiale journal.
Applications can be made by a student enrolled full-time in a PhD programme
at an Italian University.
The applicant must be a member of the Association for 2016.
If she/he is not a member for 2016 she/he must register before applying.
Funding is available for 2 students.
The visit start should be between the 1st July 2016 and the 30th of June
2017.
Deadline for applications: 10 June 2016
Notification of grants: 22 June 2016
The information required in the application are:
1. name of the Italian PhD student who will go abroad;
2. name of the foreign researcher that will host the student;
3. name and address of the foreign Lab/Department and University;
4. a short (max 2 pages) resume/CV of the Italian student;
5. a short (max 2 pages) resume/CV of the foreign researcher;
6. a short (max 2 pages) description of the research that will be carried
out
during the visit
7. a budget of the foreseen expenses
8. declaration of the foreign host indicating that the hosting institution
is
willing to provide office space and access to lab facilities to conduct
the
research
9. expected visit dates
The application must be sent by email to out...@ai...
The applications will be examined by a committee composed by members of the
AI*IA Board of Directors.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
|
From: Fabrizio R. <fab...@un...> - 2016-06-01 06:34:58
|
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
AI*IA Incoming Mobility Grants 2016
Call for research visits
Deadline for applications: 10 June 2016
https://sites.google.com/a/aixia.it/italiano/premi/incoming-mobility
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
To favour mobility of young researchers the Italian Association for
Artificial
Intelligence (AI*IA) issues the Association Incoming Mobility Grants for
2015.
Applications are solicited for funding a research visit of a PhD student
enrolled at a foreign University to an Italian institution.
Students will be funded by AI*IA which will cover their travel costs and
living
expenses (up to 2000 euro).
The funding will be provided as a reimbursement for the expenses incurred
in the
visit. After the visit, the awarded person should send the Association the
receipts of her/his costs for which she/he would like to be refunded.
The central aim of these extended visits is to build a research bridge
between
researchers and to create a solid basis for long term collaborations.
Moreover,
the visit has to lead to a submission of an article on a joint
research topics to the Intelligenza Artificiale journal.
Eligibility for the visiting student is to be enrolled full-time in a PhD
programme at a foreign University.
Funding is available for 2 students.
The visit start should be between the 1st July 2016 and the 30th of June
2017.
Deadline for applications: 10 June 2016
Notification of grants: 22 June 2016
The information required in the application are:
1. name of the foreign PhD student who will be hosted;
2. name and address of the foreign Lab/Department and University;
3. name of the Italian researcher of the hosting institution. The Italian
researcher must be a member of the Association for 2016.
If she/he is not a member for 2016 she/he must register before applying.
4. a short (max 2 pages) resume/CV of the foreign student;
5. a short (max 2 pages) resume/CV of the Italian host;
6. a short (max 2 pages) description of the research that will be carried
out
during the visit
7. a budget of the foreseen expenses
8. declaration of the Italian host indicating that the hosting institution
is
willing to provide office space and access to lab facilities to conduct
the
research
9. expected visit dates
The application must be sent by email to inc...@ai...
The applications will be examined by a committee composed by members of the
AI*IA Board of Directors.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
|
From: Fabrizio R. <fab...@un...> - 2016-05-06 15:19:37
|
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
AI*IA Incoming Mobility Grants 2016
Call for research visits
Deadline for applications: 10 June 2016
https://sites.google.com/a/aixia.it/italiano/premi/incoming-mobility
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
To favour mobility of young researchers the Italian Association for
Artificial
Intelligence (AI*IA) issues the Association Incoming Mobility Grants for
2015.
Applications are solicited for funding a research visit of a PhD student
enrolled at a foreign University to an Italian institution.
Students will be funded by AI*IA which will cover their travel costs and
living
expenses (up to 2000 euro).
The funding will be provided as a reimbursement for the expenses incurred
in the
visit. After the visit, the awarded person should send the Association the
receipts of her/his costs for which she/he would like to be refunded.
The central aim of these extended visits is to build a research bridge
between
researchers and to create a solid basis for long term collaborations.
Moreover,
the visit has to lead to a submission of an article on a joint
research topics to the Intelligenza Artificiale journal.
Eligibility for the visiting student is to be enrolled full-time in a PhD
programme at a foreign University.
Funding is available for 2 students.
The visit start should be between the 1st July 2016 and the 30th of June
2017.
Deadline for applications: 10 June 2016
Notification of grants: 22 June 2016
The information required in the application are:
1. name of the foreign PhD student who will be hosted;
2. name and address of the foreign Lab/Department and University;
3. name of the Italian researcher of the hosting institution. The Italian
researcher must be a member of the Association for 2016.
If she/he is not a member for 2016 she/he must register before applying.
4. a short (max 2 pages) resume/CV of the foreign student;
5. a short (max 2 pages) resume/CV of the Italian host;
6. a short (max 2 pages) description of the research that will be carried
out
during the visit
7. a budget of the foreseen expenses
8. declaration of the Italian host indicating that the hosting institution
is
willing to provide office space and access to lab facilities to conduct
the
research
9. expected visit dates
The application must be sent by email to inc...@ai...
The applications will be examined by a committee composed by members of the
AI*IA Board of Directors.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
|
From: Fabrizio R. <fab...@un...> - 2016-05-06 15:14:54
|
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
AI*IA Outgoing Mobility Grants 2016
Call for research visits
Deadline for applications: 10 June 2016
https://sites.google.com/a/aixia.it/italiano/premi/outgoing-mobility
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
To favour mobility of young researchers the Italian Association for
Artificial
Intelligence (AI*IA) issues the Association Outgoing Mobility Grants for
2015.
Applications are solicited for funding a research visit abroad of a PhD
student
enrolled at an Italian University.
Students will be funded by AI*IA which will cover their travel costs and
living
expenses (up to 2000 euro).
The funding will be provided as a reimbursement for the expenses incurred
in the
visit. After the visit, the awarded person should send the Association the
receipts of her/his costs for which she/he would like to be refunded.
The central aim of these extended visits is to build a research bridge
between
researchers and to create a solid basis for long term collaborations.
Moreover,
the visit has to lead to a submission of an article on a joint
research topics to the Intelligenza Artificiale journal.
Applications can be made by a student enrolled full-time in a PhD programme
at an Italian University.
The applicant must be a member of the Association for 2016.
If she/he is not a member for 2016 she/he must register before applying.
Funding is available for 2 students.
The visit start should be between the 1st July 2016 and the 30th of June
2017.
Deadline for applications: 10 June 2016
Notification of grants: 22 June 2016
The information required in the application are:
1. name of the Italian PhD student who will go abroad;
2. name of the foreign researcher that will host the student;
3. name and address of the foreign Lab/Department and University;
4. a short (max 2 pages) resume/CV of the Italian student;
5. a short (max 2 pages) resume/CV of the foreign researcher;
6. a short (max 2 pages) description of the research that will be carried
out
during the visit
7. a budget of the foreseen expenses
8. declaration of the foreign host indicating that the hosting institution
is
willing to provide office space and access to lab facilities to conduct
the
research
9. expected visit dates
The application must be sent by email to out...@ai...
The applications will be examined by a committee composed by members of the
AI*IA Board of Directors.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
|
From: Fabrizio R. <fab...@un...> - 2016-02-29 15:42:12
|
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
AI*IA Outgoing Mobility Grants 2016
Call for research visits
Deadline for applications: 10 June 2016
https://sites.google.com/a/aixia.it/italiano/premi/outgoing-mobility
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
To favour mobility of young researchers the Italian Association for
Artificial
Intelligence (AI*IA) issues the Association Outgoing Mobility Grants for
2015.
Applications are solicited for funding a research visit abroad of a PhD
student
enrolled at an Italian University.
Students will be funded by AI*IA which will cover their travel costs and
living
expenses (up to 2000 euro).
The funding will be provided as a reimbursement for the expenses incurred
in the
visit. After the visit, the awarded person should send the Association the
receipts of her/his costs for which she/he would like to be refunded.
The central aim of these extended visits is to build a research bridge
between
researchers and to create a solid basis for long term collaborations.
Moreover,
the visit has to lead to a submission of an article on a joint
research topics to the Intelligenza Artificiale journal.
Applications can be made by a student enrolled full-time in a PhD programme
at an Italian University.
The applicant must be a member of the Association for 2016.
If she/he is not a member for 2016 she/he must register before applying.
Funding is available for 2 students.
The visit start should be between the 1st July 2016 and the 30th of June
2017.
Deadline for applications: 10 June 2016
Notification of grants: 22 June 2016
The information required in the application are:
1. name of the Italian PhD student who will go abroad;
2. name of the foreign researcher that will host the student;
3. name and address of the foreign Lab/Department and University;
4. a short (max 2 pages) resume/CV of the Italian student;
5. a short (max 2 pages) resume/CV of the foreign researcher;
6. a short (max 2 pages) description of the research that will be carried
out
during the visit
7. a budget of the foreseen expenses
8. declaration of the foreign host indicating that the hosting institution
is
willing to provide office space and access to lab facilities to conduct
the
research
9. expected visit dates
The application must be sent by email to out...@ai...
The applications will be examined by a committee composed by members of the
AI*IA Board of Directors.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
|
From: Fabrizio R. <fab...@un...> - 2016-02-29 15:41:17
|
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
AI*IA Incoming Mobility Grants 2016
Call for research visits
Deadline for applications: 10 June 2016
https://sites.google.com/a/aixia.it/italiano/premi/incoming-mobility
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
To favour mobility of young researchers the Italian Association for
Artificial
Intelligence (AI*IA) issues the Association Incoming Mobility Grants for
2015.
Applications are solicited for funding a research visit of a PhD student
enrolled at a foreign University to an Italian institution.
Students will be funded by AI*IA which will cover their travel costs and
living
expenses (up to 2000 euro).
The funding will be provided as a reimbursement for the expenses incurred
in the
visit. After the visit, the awarded person should send the Association the
receipts of her/his costs for which she/he would like to be refunded.
The central aim of these extended visits is to build a research bridge
between
researchers and to create a solid basis for long term collaborations.
Moreover,
the visit has to lead to a submission of an article on a joint
research topics to the Intelligenza Artificiale journal.
Eligibility for the visiting student is to be enrolled full-time in a PhD
programme at a foreign University.
Funding is available for 2 students.
The visit start should be between the 1st July 2016 and the 30th of June
2017.
Deadline for applications: 10 June 2016
Notification of grants: 22 June 2016
The information required in the application are:
1. name of the foreign PhD student who will be hosted;
2. name and address of the foreign Lab/Department and University;
3. name of the Italian researcher of the hosting institution. The Italian
researcher must be a member of the Association for 2016.
If she/he is not a member for 2016 she/he must register before applying.
4. a short (max 2 pages) resume/CV of the foreign student;
5. a short (max 2 pages) resume/CV of the Italian host;
6. a short (max 2 pages) description of the research that will be carried
out
during the visit
7. a budget of the foreseen expenses
8. declaration of the Italian host indicating that the hosting institution
is
willing to provide office space and access to lab facilities to conduct
the
research
9. expected visit dates
The application must be sent by email to inc...@ai...
The applications will be examined by a committee composed by members of the
AI*IA Board of Directors.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=
|
|
From: Lorenz B. <spo...@st...> - 2016-02-10 09:27:01
|
* Dear all, the AKSW group [1] is happy to announce DL-Learner 1.2. DL-Learner is a framework containing algorithms for supervised machine learning in RDF and OWL. DL-Learner can use various RDF and OWL serialization formats as well as SPARQL endpoints as input, can connect to most popular OWL reasoners and is easily and flexibly configurable. It extends concepts of Inductive Logic Programming and Relational Learning to the Semantic Web in order to allow powerful data analysis. Website: http://dl-learner.org GitHub page: https://github.com/AKSW/DL-Learner Download: https://github.com/AKSW/DL-Learner/releases ChangeLog: http://dl-learner.org/development/changelog/ DL-Learner is used for data analysis tasks within other tools such as ORE [2] and RDFUnit [3]. Technically, it uses refinement operator based, pattern-based and evolutionary techniques for learning on structured data. For a practical example, see [4]. DL-Learner also offers a plugin for Protégé [5], which can give suggestions for axioms to add. DL-Learner is part of the Linked Data Stack [6] - a repository for Linked Data management tools. In the current release, we improved the support for SPARQL endpoints as knowledge sources. You can now directly use a SPARQL endpoint for learning without an OWL reasoner on top of it. Moreover, we extended DL-Learner to also consider dates and inverse properties for learning. Further efforts were made to improve our Query Tree Learning algorithms (those are used to learn SPARQL queries rather than OWL class expressions). We want to thank everyone who helped to create this release, in particular Robert Höhndorf and Giuseppe Rizzo. We also acknowledge support by the recently started SAKE project, in which DL-Learner will be applied to event analysis in manufacturing use cases, as well as the GeoKnow [7] and Big Data Europe [8] projects where it is part of the respective platforms. ** *View this announcement on Twitter and the AKSW blog:* https://twitter.com/dllearner/status/697081711805468674 http://blog.aksw.org/dl-learner-1-2/ Kind regards, ** Lorenz Bühmann, Jens Lehmann, Patrick Westphal and Simon Bin [1] http://aksw.org [2] http://ore-tool.net [3] http://aksw.org/Projects/RDFUnit.html [4] http://dl-learner.org/community/carcinogenesis/ [5] https://github.com/AKSW/DL-Learner-Protege-Plugin [6] http://stack.linkeddata.org [7] http://geoknow.eu [8] http://www.big-data-europe.eu* |
8 messages has been excluded from this view by a project administrator.
