Re: [Cuitools-users] lower case and other small things (in --help)

[Ted P. <tpederse@d.umn.edu>]

Thanks Bridget,

This all sounds good!

Ted

On Wed, Jul 23, 2008 at 12:15 PM, Bridget Thomson McInnes
<bth...@cs...> wrote:
> Hi Ted,
>
>> Do we have any way to convert the text to lower case? If not that's
>> fairly easy to do, but couldn't remember if that was something we had
>> included or not...
>>
>
> We do. I am sorry it didn't get into the supervised-disambiguate
> documentation. It is the --lc option.
>
>> Also, in the help for supervised-disambiguate.pl - there are two
>> entries for --mesh, there isn't a space under the --wekacv entry,
>> and a few of the left hand margins are slightly off (some indented
>> once, others not at all, something like that...) The entry for
>> --cv has a kind of funny line break in it...--nokey seems to have a
>> repeated word (This) Very very minor cosmetic issues.
>>
>
> Thanks! I made the changes to these in the documentation.
>
>> Slightly (but just barely) more substantial issues in the --help are
>> that I don't think it makes it clear that SOURCE can either be a
>> directory containing lots of .mm files or a single .mm file...and it
>> also says that at least one feature must be selected - however,
>> it will run ok with just the SOURCE indicated, so we should probably
>> make it clear what will happen if you just give it SOURCE.
>> --version shows copyright as 2007 but we probably want that to be
>> 2007-2008 at this point, and you should list yourself as
>> first author on copyright and other stuff...
>>
>
> I fixed the copyright in the version number.
>
> And added to the perldoc and help
>
> If no feature option is chosen, the default feature setting
> is used:
>
>    --ngramcount "--ngram 1 --frequency 2"
>
> in order to be clear that no feature option is required to run the
> supervised-disambiguate.pl program.
>
> I also A directory containing the CuiTools xml-like .mm formatted
> training file(s) or a single file in the CuiTools xml-like
> .mm format.
>
> I modified the help and the perldoc description to be more
> clear that SOURCE can be either a directory containing the
> .mm files or a single .mm file.
>
> Here is what I wrote:
>
> This is a wrapper program for supervised WSD using CuiTools
> programs. It takes as input (SOURCE) a directory containing
> files in the CuiTools xml-like .mm format or a single file
> in the xml-like .mm format. The program extracts specified
> features and trains/tests a classifier using the WEKA data
> mining package. The overall results are stored in a file
> called overallResults located in the results directory. If
> no feature option is chosen, the default feature setting is
> used: --ngramcount "--ngram 1 --frequency 2"
>
> I hope this makes the documentation clearer.
>
> Thanks!
>
> Bridget
>



-- 
Ted Pedersen
http://www.d.umn.edu/~tpederse