It should be possible to map to these from the output of our tagger,
this way you can write mostly language independent code.
We would be more than happy to receive contributions to make the usage
of general tag sets easier with our POS Tagger. It would probably not a big
deal to build the mapping layer directly into the model, then you do not
need any special handling at all in your own code.
Jörn
On 01/24/2013 12:06 PM, Svetoslav Marinov wrote:
You may look at Google's initiative for universal tagsets:
http://code.google.com/p/universal-pos-tags/
Could share a bit more about your work in document summarization? I am
personally interested in this.
Best,
Svetoslav
On 2013-01-24 11:59, "Renzo" <[email protected]> wrote:
Hi all,
I'm pretty new to OpenNLP.
My interest is almost related to fetch document summaries using
algorithms such as TextRank.
This task requires sentence and token splitting - here's where OpenNLP
enters the game.
I also need some degree of POS to detect nouns, verbs and so on, in
order to add some linguistic support to the ranking process.
It was fairly surprising to discover that noun tags - for example - are
language dependent. Thus an "isNoun" predicate needs a specific answer
for each language. It's "NN" for English, but it may be different for
others.
I just wonder if there is a common (e.g. language-independent) way to
answer such a kind of questions.
Furthermore, is the logical format of available binary files documented
anywhere ? Is there any way to browse those files to inspect the used
tag list ?
Thanks,
Renzo
