Similarity-based estimation of word cooccurrence probabilities

I. Dagan, Fernando Pereira, Lillian Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


In many applications of natural language processing it is necessary to determine the likelihood of a given word combination. For example, a speech recognizer may need to determine which of the two word combinations "eat a peach" and "eat a beach" is more likely. Statistical NLP methods determine the likelihood of a word combination according to its frequency in a training corpus. However, the nature of language is such that many word combinations are infrequent and do not occur in a given corpus. In this work we propose a method for estimating the probability of such previously unseen word combinations using available information on "most similar" words.We describe a probabilistic word association model based on distributional word similarity, and apply it to improving probability estimates for unseen word bigrams in a variant of Katz's back-off model. The similarity-based method yields a 20% perplexity improvement in the prediction of unseen bigrams and statistically significant reductions in speech-recognition error.
Original languageAmerican English
Title of host publication32nd annual meeting on Association for Computational Linguistics
PublisherAssociation for Computational Linguistics
StatePublished - 1994

Bibliographical note

Place of conference:Las Cruces, New Mexico


Dive into the research topics of 'Similarity-based estimation of word cooccurrence probabilities'. Together they form a unique fingerprint.

Cite this