I wish to take the POS tagged sentences from a document and break/assemble it into simple Subject, Object, Predicate.
Is there anything ready-made in NLP world, or even OpenNLP, that i could readily use?
Would the chunker be the right component? Where could i find some literature regarding some basic theory of Chunker, some usage, example/tutorial (i wish :) ), anything?
Any help is appreciated.
Regards,
Nitin
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I'm not positive, but I don't think the Chunker is going to be enough for you. You might want to try out Tom's parser (in opennlp tools) which produces a Penn Treebank style parse. This should provide enough information to get what you want.
I've never used this myself, but there are some simple instructions in the OpenNLP README file. I think that the annotations are described in ftp://ftp.cis.upenn.edu/pub/treebank/doc/manual/root.ps.gz.
Gann
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
I wish to take the POS tagged sentences from a document and break/assemble it into simple Subject, Object, Predicate.
Is there anything ready-made in NLP world, or even OpenNLP, that i could readily use?
Would the chunker be the right component? Where could i find some literature regarding some basic theory of Chunker, some usage, example/tutorial (i wish :) ), anything?
Any help is appreciated.
Regards,
Nitin
I'm not positive, but I don't think the Chunker is going to be enough for you. You might want to try out Tom's parser (in opennlp tools) which produces a Penn Treebank style parse. This should provide enough information to get what you want.
I've never used this myself, but there are some simple instructions in the OpenNLP README file. I think that the annotations are described in ftp://ftp.cis.upenn.edu/pub/treebank/doc/manual/root.ps.gz.
Gann