Word Association Norms, Mutual Information, and Lexicography
Church & Hanks, 1990, Word Association Norms, Mutual Information, and Lexicography (Computational Linguistics)
Subscriber deck — free during early access
2 cards in “5 Lexico-syntactic regularities” · whole deck
5 Lexico-syntactic regularities
- How does the association ratio formalize Sinclair’s argument about phrasal verbs like set off?Sinclair compared the observed probability of set off with the tiny chance probability \(P(set)P(off)\) if words were distributed at random. Mutual information measures exactly that: \(I(set; off) \approx 6.1\) in Sinclair’s corpus and 6.2 in AP news, more than \(2^6 = 64\) times chance.
- Church & Hanks, 1990, Word Association Norms, Mutual Information, and Lexicography (Computational Linguistics), §5, p. 25
- What did the association ratio show for set + particle?Set up, set off and set out are clearly associated; set on, set in and set about are not so clear, so the approach suits finding phrasal verbs, at least in some cases.
- Church & Hanks, 1990, Word Association Norms, Mutual Information, and Lexicography (Computational Linguistics), §5, p. 25
Source
- Kenneth Ward Church and Patrick Hanks. 1990. Word Association Norms, Mutual Information, and Lexicography. In Computational Linguistics, pp. 22–29. https://aclanthology.org/J90-1003/