Computer Science – Computation and Language
Scientific paper
1997-06-13
Computer Science
Computation and Language
8 pages, LaTeX source and postscript figures for ACL/EACL'97 paper
Scientific paper
This 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.
Beeferman Doug
Berger Adam
Lafferty John
No associations
LandOfFree
A Model of Lexical Attraction and Repulsion does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A Model of Lexical Attraction and Repulsion, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Model of Lexical Attraction and Repulsion will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-148970