One Sense per Collocation and Genre/Topic Variations

Simple item page
dc.creatorMartinez, David
dc.creatorAgirre, Eneko
dc.date2000-10-17
dc.date.accessioned2026-07-07T03:16:38Z
dc.date.available2026-07-07T03:16:38Z
dc.descriptionThis paper revisits the one sense per collocation hypothesis using fine-grained sense distinctions and two different corpora. We show that the hypothesis is weaker for fine-grained sense distinctions (70% vs. 99% reported earlier on 2-way ambiguities). We also show that one sense per collocation does hold across corpora, but that collocations vary from one corpus to the other, following genre and topic variations. This explains the low results when performing word sense disambiguation across corpora. In fact, we demonstrate that when two independent corpora share a related genre/topic, the word sense disambiguation results would be better. Future work on word sense disambiguation will have to take into account genre and topic as important parameters on their models.
dc.description9 pages
dc.identifierhttps://arxiv.org/abs/cs/0010027
dc.identifierhttp://arxiv.org/abs/cs/0010027
dc.identifierProceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora 2000
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/30430
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleOne Sense per Collocation and Genre/Topic Variations
dc.typetext

Files

Collections

arXiv