Unsupervised Word Sense Disambiguation Rivaling Supervised Methods
Yarowsky, 1995, Unsupervised Word Sense Disambiguation Rivaling Supervised Methods (Proceedings of the 33rd Annual Meeting of ACL)
Subscriber deck — free during early access
2 cards in “2 One sense per discourse” · whole deck
2 One sense per discourse
- How was the one-sense-per-discourse hypothesis measured?By accuracy (when a word occurs more than once in a discourse, how often it takes the discourse’s majority sense: very high) and applicability (how often it occurs more than once in a discourse at all: about half the time).
- Yarowsky, 1995, Unsupervised Word Sense Disambiguation Rivaling Supervised Methods (Proceedings of the 33rd Annual Meeting of ACL), §2
- Why might words keep one sense per discourse?Mostly statistics: two distinct terms of moderate frequency rarely co-occur in a discourse anyway, especially “bursty” content words. But writers also seem to avoid mixing senses: homograph pairs co-occurred about 5 times less often than comparable arbitrary word pairs.
- Yarowsky, 1995, Unsupervised Word Sense Disambiguation Rivaling Supervised Methods (Proceedings of the 33rd Annual Meeting of ACL), §2
Source
- David Yarowsky. 1995. Unsupervised Word Sense Disambiguation Rivaling Supervised Methods. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, pp. 189–196. https://aclanthology.org/P95-1026/