A Model of Lexical Attraction and Repulsion

dc.creatorBeeferman, Doug
dc.creatorBerger, Adam
dc.creatorLafferty, John
dc.date1997-06-13
dc.date1997-06-16
dc.date.accessioned2026-07-07T09:02:23Z
dc.date.available2026-07-07T09:02:23Z
dc.descriptionThis paper introduces new methods based on exponential families for modeling the correlations between words in text and speech. While previous work assumed the effects of word co-occurrence statistics to be constant over a window of several hundred words, we show that their influence is nonstationary on a much smaller time scale. Empirical data drawn from English and Japanese text, as well as conversational speech, reveals that the ``attraction'' between words decays exponentially, while stylistic and syntactic contraints create a ``repulsion'' between words that discourages close co-occurrence. We show that these characteristics are well described by simple mixture models based on two-stage exponential distributions which can be trained using the EM algorithm. The resulting distance distributions can then be incorporated as penalizing features in an exponential language model.
dc.description8 pages, LaTeX source and postscript figures for ACL/EACL'97 paper
dc.identifierhttps://arxiv.org/abs/cmp-lg/9706018
dc.identifierhttp://arxiv.org/abs/cmp-lg/9706018
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/148611
dc.subjectComputation and Language
dc.titleA Model of Lexical Attraction and Repulsion
dc.typetext

Files

Collections