Word Association Norms, Mutual Information, and Lexicography

8 Applications in lexicography

1. What were the limits of lexicography with concordances (KWIC indexes) in the 1980s?
   Lexicographers marked up printouts with coloured pens to find senses. This works for a few dozen lines and two or three senses, but for words like take, save or from the patterns are buried in thousands of lines, beyond what the unaided mind can find and rank.
   • Church & Hanks, 1990, Word Association Norms, Mutual Information, and Lexicography (Computational Linguistics), §8, p. 26
2. What does save … from illustrate?
   Association norms apply to function words too: from is significantly associated with save (about 21 times chance), yet save ranks only 319th among verbs associated with from, strong enough to matter but not to pop out of a concordance. Many dictionaries don’t mention it.
   • Church & Hanks, 1990, Word Association Norms, Mutual Information, and Lexicography (Computational Linguistics), §8, pp. 26–27
3. How did association scores reveal gaps in a dictionary?
   Of the 27 bare verbs among the top 100 associated with from, the Cobuild dictionary listed all but seven with from (missing e.g. vary, ferry, strip, divert, forbid, reap). The measure could improve coverage at lower cost.
   • Church & Hanks, 1990, Word Association Norms, Mutual Information, and Lexicography (Computational Linguistics), §8, p. 27
4. How did association scores help find semantic classes for save’s concordance lines?
   The tags the authors invented (save PERSON from BAD, save INSTITUTION from ECONOMIC BAD, save ANIMAL from DESTRUCTION) could mostly have been suggested by the association table. It also pointed to patterns they had missed, such as time adverbials (annually, month) going with MONEY objects, and save the forests (ENVIRONMENT).
   • Church & Hanks, 1990, Word Association Norms, Mutual Information, and Lexicography (Computational Linguistics), §8, pp. 27–28