A Uniform Approach to Analogies, Synonyms, Antonyms, and Associations

Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 905–912 Manchester, August 2008 A Uniform Approach to Analogies, Synonyms, Antonyms, and Associations Peter D. Turney National Research Council of Canada Institute for Information Technology M50 Montreal Road Ottawa, Ontario, Canada K1A 0R6 peter.turney@nrc-cnrc.gc.ca Abstract Recognizing analogies, synonyms, anto- nyms, and associations appear to be four distinct tasks, requiring distinct NLP al- gorithms. In the past, the four tasks have been treated independently, using a wide variety of algorithms. These four seman- tic classes, however, are a tiny sample of the full range of semantic phenomena, and we cannot afford to create ad hoc algo- rithms for each semantic phenomenon; we need to seek a unified approach. We pro- pose to subsume a broad range of phenom- ena under analogies. To limit the scope of this paper, we restrict our attention to the subsumption of synonyms, antonyms, and associations. We introduce a supervised corpus-based machine learning algorithm for classifying analogous word pairs, and we show that it can solve multiple-choice SAT analogy questions, TOEFL synonym questions, ESL synonym-antonym ques- tions, and similar-associated-both ques- tions from cognitive psychology. 1 Introduction A pair of words (petrify:stone) is analogous to an- other pair (vaporize:gas) when the semantic re- lations between the words in the first pair are highly similar to the relations in the second pair. Two words (levied and imposed) are synonymous in a context (levied a tax) when they can be in- terchanged (imposed a tax), they are are antony- mous when they have opposite meanings (black c⃝ 2008, National Research Council of Canada (NRC). Licensed to the Coling 2008 Organizing Committee for pub- lication in Coling 2008 and for re-publishing in any form or medium. and white), and they are associated when they tend to co-occur (doctor and hospital). On the surface, it appears that these are four dis- tinct semantic classes, requiring distinct NLP al- gorithms, but we propose a uniform approach to all four. We subsume synonyms, antonyms, and associations under analogies. In essence, we say that X and Y are antonyms when the pair X:Y is analogous to the pair black:white, X and Y are synonyms when they are analogous to the pair levied:imposed, and X and Y are associated when they are analogous to the pair doctor:hospital. There is past work on recognizing analogies (Reitman, 1965), synonyms (Landauer and Du- mais, 1997), antonyms (Lin et al., 2003), and asso- ciations (Lesk, 1969), but each of these four tasks has been examined separately, in isolation from the others. As far as we know, the algorithm proposed here is the first attempt to deal with all four tasks using a uniform approach. We believe that it is important to seek NLP algorithms that can han- dle a broad range of semantic phenomena, because developing a specialized algorithm for each phe- nomenon is a very inefficient research strategy. It might seem that a lexicon, such as Word- Net (Fellbaum, 1998), contains all the information we need to …

Content truncated to 500 words