Computer Science – Computation and Language
Scientific paper
2000-10-17
Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora 2000
Computer Science
Computation and Language
9 pages
Scientific paper
This 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.
Agirre Eneko
Martinez David
No associations
LandOfFree
One Sense per Collocation and Genre/Topic Variations does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with One Sense per Collocation and Genre/Topic Variations, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and One Sense per Collocation and Genre/Topic Variations will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-398566