In particular POS tagging, dependency and constituent parsing. This is not really my field of study but I would really like to be able to make informed claims on what precisions current top systems achieve (and what top systems for each task are).

This paper of a (high quality) system (http://arxiv.org/abs/1103.0398) we have used in experiements uses benchmarks from 2000, 2003 and 2005. But I don't know if more recent systems have outperformed those or new benchmark tasks exists.

  • 1
    $\begingroup$ Have you google-scholar-ed? $\endgroup$ – Raphael Jul 15 '14 at 15:56

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.