A method for disambiguating word senses in a large corpus

Abstract

Word sense disambiguation has been recognized as a major problem in natural language processing research for over forty years. Both quantitive and qualitative methods have been tried, but much of this work has been stymied by difficulties in acquiring appropriate lexical resources, such as semantic networks and annotated corpora. In particular, much of the work on qualitative methods has had to focus on ''toy'' domains since currently available semantic networks generally lack broad coverage. Similarly, much of the work on quantitative methods has had to depend on small amounts of hand-labeled text for testing and training.We have achieved considerable progress recently by taking advantage of a new source of testing and training materials. Rather than depending on small amounts of hand-labeled text, we have been making use of relatively large amounts of parallel text, text such as the Canadian Hansards, which are available in multiple languages. The translation can often be used in lieu of hand-labeling. For example, consider the polysemous word sentence, which has two major senses: (1) a judicial sentence, and (2), a syntactic sentence. We can collect a number of sense (1) examples by extracting instances that are translated as peine, and we can collect a number of sense (2) examples by extracting instances that are translated as phrase. In this way, we have been able to acquire a considerable amount of testing and training material for developing and testing our disambiguation algorithms.The availability of this testing and training material has enabled us to develop quantitative disambiguation methods that achieve 92 percent accuracy in discriminating between two very distinct senses of a noun such as sentence. In the training phase, we collect a number of instances of each sense of the polysemous noun. Then in the testing phase, we are given a new instance of the noun, and are asked to assign the instance to one of the senses. We attempt to answer this question by comparing the context of the unknown instance with contexts of known instances using a Bayesian argument that has been applied successfully in related tasks such as author identification and information retrieval.The Bayesian classifier requires an estimate of Pr(w  sense), the probability of finding the word w in a particular context. Care must be taken in estimating these probabilities since there are so many parameters (e.g., 100,000 for each sense) and so little training material (e.g., 5,000 words for each sense). We have found that it helps to smooth the estimates obtained from the training material with estimates obtained from the entire corpus. The idea is that the training material provides poorly measured estimates, whereas the entire corpus provides less relevant estimates. We seek a trade-off between measurement errors and relevance using a novel interpolation procedure that has one free parameter, an estimate of how much the conditional probabilities Pr(w  sense) will differ from the global probabilities Pr(w). In the sense t...

Evaluation of automatic updates of Roget’s Thesaurus

“…That can be useful in real WSD. Others who have worked on variations of PWSD include Gale et al (1992); Schütze (1998); Lee (1999); Dagan et al (1999); Rooth et al (1999); Clark and Weir (2002); Weeds and Weir (2005); ZhitomirskyGeffet and Dagan (2009). The methodology we followed was similar to that of Weeds and Weir.…”

Text and Hypertext Categorization

“…TC is used in many application contexts, ranging from automatic document indexing based on a controlled vocabulary (Borko and Bernick 1963;Gray and Harley 1971;Field 1975), to document filtering (Amati and Crestani 1999;Iyer, Lewis et al 2000;Kim, Hahn et al 2000), word sense disambiguation (Gale, Church et al 1992;Escudero, Marquez et al 2000), population of hierarchical catalogues of Web resources (Chakrabarti, Dom et al 1998;Attardi, Gulli et al 1999;Oh, Myaeng et al 2000), and in general any application requiring document organization or selective and adaptive document dispatching.…”

Untitled

“…A number of methods have been proposed, either for context-sensitive spelling correction directly, or for related lexical disambiguation tasks. The methods include word trigrams (Mays, Damerau, & Mercer, 1991), Bayesian classifiers (Gale, Church, & Yarowsky, 1993), decision lists (Yarowsky, 1994), Bayesian hybrids (Golding, 1995), a combination of part-of-speech trigrams and Bayesian hybrids (Golding & Schabes, 1996), and, more recently, transformation-based learning (Mangu & Brill, 1997), latent semantic analysis (Jones & Martin, 1997), and differential grammars (Powers, 1997). While these research systems have gradually been achieving higher levels of accuracy, we believe that a Winnow-based approach is particularly promising for this problem, due to the problem's need for a very large number of features to characterize the context in which a word occurs, and Winnow's theoretically-demonstrated ability to handle such large numbers of features.…”