4
$\begingroup$

I need to do coreference resolution for German texts and I plan to use OpenNLP to perform this task.

As far as I know OpenNLP coreference resolution does not support the German language.

Which components/data do I need to adapt the code such that it is possible to perform coreference resolution for German texts?

Improve this question
$\endgroup$
5
  • 1
    $\begingroup$ possible duplicate of Coreference Resolution for German Texts $\endgroup$
    – ffriend
    Commented Aug 11, 2014 at 15:19
  • $\begingroup$ It is not a duplicate. It is a question specific to OpenNLP and the other question is about coreference resolution tools in general $\endgroup$
    – Pasmod Turing
    Commented Aug 12, 2014 at 10:57
  • $\begingroup$ I can't see the difference between these questions. Both ask for a coreference tool besides OpenNLP, because OpenNLP doesn't support it. $\endgroup$
    – Sean Owen
    Commented Aug 12, 2014 at 11:20
  • $\begingroup$ This question asks about training methods to add the coref resolution functionality to OpenNLP and the other one asks for available tools for German coreference resolution. This is a big difference! $\endgroup$
    – Pasmod Turing
    Commented Aug 12, 2014 at 15:11
  • 1
    $\begingroup$ OK. I suggest rewording these to make them more distinct. I think many readers will not get the nuance of what you are asking in each case. $\endgroup$
    – Sean Owen
    Commented Aug 13, 2014 at 12:17

1 Answer 1

Reset to default
1
$\begingroup$

From an older version of the OpenNLP README:

Training the Tools

There are training tools for all components expect the coref component. Please consult the help message of the tool and the javadoc to figure out how to train the tools.

The tutorials in our wiki might also be helpful.

The following modules currently support training via the WordFreak opennlp.plugin v1.4 (http://wordfreak.sourceforge.net/plugins.html).

  • coreference: org.annotation.opennlp.OpenNlpCoreferenceAnnotator (use opennlp 1.4.3 for training, models are compatible)

Note: In order to train a model you need all the training data. There is not currently a mechanism to update the models distributed with the project with additional data.

As you can see, OpenNLP does not provide training tools for the coreference component. However, it seems at one point it was possible to train new models for OpenNLP's coref component using the third-party WordFreak plugin... however, it hasn't been updated in over a decade, so your mileage may vary.

Improve this answer
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.