Similarity-Based Models of Word Cooccurrence Probabilities

dc.creatorDagan, Ido
dc.creatorLee, Lillian
dc.creatorPereira, Fernando C. N.
dc.date1998-09-27
dc.date.accessioned2026-07-07T03:23:40Z
dc.date.available2026-07-07T03:23:40Z
dc.descriptionIn many applications of natural language processing (NLP) 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 from its frequency in a training corpus. However, the nature of language is such that many word combinations are infrequent and do not occur in any 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 probabilistic word association models based on distributional word similarity, and apply them to two tasks, language modeling and pseudo-word disambiguation. In the language modeling task, a similarity-based model is used to improve probability estimates for unseen bigrams in a back-off language model. The similarity-based method yields a 20% perplexity improvement in the prediction of unseen bigrams and statistically significant reductions in speech-recognition error. We also compare four similarity-based estimation methods against back-off and maximum-likelihood estimation methods on a pseudo-word sense disambiguation task in which we controlled for both unigram and bigram frequency to avoid giving too much weight to easy-to-disambiguate high-frequency configurations. The similarity-based methods perform up to 40% better on this particular task.
dc.description26 pages, 5 figures
dc.identifierhttps://arxiv.org/abs/cs/9809110
dc.identifierhttp://arxiv.org/abs/cs/9809110
dc.identifierMachine Learning, 34, 43-69 (1999)
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/33038
dc.subjectComputation and Language
dc.subjectArtificial Intelligence
dc.subjectMachine Learning
dc.subjectI.2.7;I.2.6
dc.titleSimilarity-Based Models of Word Cooccurrence Probabilities
dc.typetext

Files

Collections