Using Verb Subcategorization for Word Sense Disambiguation

Will Roberts, Valia Kordoni


Abstract
We develop a model for predicting verb sense from subcategorization information and integrate it into SSI-Dijkstra, a wide-coverage knowledge-based WSD algorithm. Adding syntactic knowledge in this way should correct the current poor performance of WSD systems on verbs. This paper also presents, for the first time, an evaluation of SSI-Dijkstra on a standard data set which enables a comparison of this algorithm with other knowledge-based WSD systems. Our results show that our system is competitive with current graph-based WSD algorithms, and that the subcategorization model can be used to achieve better verb sense disambiguation performance.
Anthology ID:
L12-1112
Volume:
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)
Month:
May
Year:
2012
Address:
Istanbul, Turkey
Venue:
LREC
SIG:
Publisher:
European Language Resources Association (ELRA)
Note:
Pages:
829–832
Language:
URL:
http://www.lrec-conf.org/proceedings/lrec2012/pdf/269_Paper.pdf
DOI:
Bibkey:
Cite (ACL):
Will Roberts and Valia Kordoni. 2012. Using Verb Subcategorization for Word Sense Disambiguation. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 829–832, Istanbul, Turkey. European Language Resources Association (ELRA).
Cite (Informal):
Using Verb Subcategorization for Word Sense Disambiguation (Roberts & Kordoni, LREC 2012)
Copy Citation:
PDF:
http://www.lrec-conf.org/proceedings/lrec2012/pdf/269_Paper.pdf