Broad-Coverage Sense Disambiguation and Information Extraction with a Supersense Sequence Tagger
2006
Conference Paper
ei
In this paper we approach word sense disambiguation and information extraction as a unified tagging problem. The task consists of annotating text with the tagset defined by the 41 Wordnet supersense classes for nouns and verbs. Since the tagset is directly related to Wordnet synsets, the tagger returns partial word sense disambiguation. Furthermore, since the noun tags include the standard named entity detection classes – person, location, organization, time, etc. – the tagger, as a by-product, returns extended named entity information. We cast the problem of supersense tagging as a sequential labeling task and investigate it empirically with a discriminatively-trained Hidden Markov Model. Experimental evaluation on the main sense-annotated datasets available, i.e., Semcor and Senseval, shows considerable improvements over the best known “first-sense” baseline.
Author(s): | Ciaramita, M. and Altun, Y. |
Pages: | 594-602 |
Year: | 2006 |
Month: | July |
Day: | 0 |
Editors: | Jurafsky, D. , E. Gaussier |
Publisher: | Association for Computational Linguistics |
Department(s): | Empirical Inference |
Bibtex Type: | Conference Paper (inproceedings) |
Event Name: | 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006) |
Event Place: | Sydney, Australia |
Address: | Stroudsburg, PA, USA |
Digital: | 0 |
Links: |
Web
|
BibTex @inproceedings{CiaramitaA2006, title = {Broad-Coverage Sense Disambiguation and Information Extraction with a Supersense Sequence Tagger}, author = {Ciaramita, M. and Altun, Y.}, pages = {594-602}, editors = {Jurafsky, D. , E. Gaussier}, publisher = { Association for Computational Linguistics}, address = {Stroudsburg, PA, USA}, month = jul, year = {2006}, doi = {}, month_numeric = {7} } |