Word sense disambiguation using cross-lingual information

Nancy Ide
Department of Computer Science
Vassar College
Poughkeepsie, New York 12604-0520
Ide@cs.vassar.edu

It is well known that the most nagging issue for word sense disambiguation (WSD) is the definition of just what a word sense is. At its base, the problem is a philosophical and linguistic one that is far from being resolved. However, work in automated language processing has led to efforts to find practical means to distinguish word senses, at least to the degree that they are useful for natural language processing tasks such as summarization, document retrieval, and machine translation. Several criteria have been suggested and exploited to automatically determine the sense of a word in context, including syntactic behavior, semantic and pragmatic knowledge, and especially in more recent empirical studies, word co-occurrence within syntactic relations (e.g., Hearst, 1991; Yarowsky, 1993), words co-occurring in global context (e.g., Gale et al., 1993; Yarowsky, 1992; Schütze, 1992, 1993), etc. No clear criteria have emerged, however, and the problem continues to loom large for WSD work.

The notion that cross-lingual comparison can be useful for sense disambiguation has served as a basis for some recent work on WSD. For example, Brown et al. (1991) and Gale et al. (1992a, 1993) used the parallel, aligned Hansard Corpus of Canadian Parliamentary debates for WSD, and Dagan et al. (1991) and Dagan and Itai (1994) used monolingual corpora of Hebrew and German and a bilingual dictionary. These studies rely on the assumption that the mapping between words and word senses varies significantly among languages. For example, the word duty in English translates into French as devoir in its obligation sense, and impôt in its tax sense. By determining the translation equivalent of duty in a parallel French text, the correct sense of the English word is identified. These studies exploit this information in order to gather co-occurrence data for the different senses, which is then used to disambiguate new texts. In related work, Dyvik (1998) used patterns of translational relations in an English-Norwegian parallel corpus (ENPC, Oslo University) to define semantic properties such as synonymy, ambiguity, vagueness, and semantic fields and suggested a derivation of semantic representations for signs (e.g., lexemes), capturing semantic relationships such as hyponymy etc., from such translational relations.

Recently, Resnik and Yarowsky (1997) suggested that for the purposes of WSD, the different senses of a word could be determined by considering only sense distinctions that are lexicalized cross-linguistically. In particular, they propose that some set of target languages be identified, and that the sense distinctions to be considered for language processing applications and evaluation be restricted to those that are realized lexically in some minimum subset of those languages. This idea would seem to provide an answer, at least in part, to the problem of determining different senses of a word: intuitively, one assumes that if another language lexicalizes a word in two or more ways, there must be a conceptual motivation. If we look at enough languages, we would be likely to find the significant lexical differences that delimit different senses of a word.

However, this suggestion raises several questions. For instance, it is well known that many ambiguities are preserved across languages (for example, the French intérêt and the English interest), especially languages that are relatively closely related, such as English and French. Assuming this problem can be overcome, should differences found in closely related languages be given lesser (or greater) weight than those found in more distantly related languages? More generally, which languages should be considered for this exercise? All languages? Closely related languages? Languages from different language families? A mixture of the two? How many languages would be "enough" to provide adequate information for this purpose?

There is also the question of the criteria that would be used to establish that a sense distinction is "lexicalized cross-linguistically". How consistent must the distinction be? Does it mean that two concepts are expressed by mutually non-interchangeable lexical items in some significant number of other languages, or need it only be the case that the option of a different lexicalization exists in a certain percentage of cases?

This paper attempts to provide some preliminary answers to these questions, in order to eventually determine the degree to which the use of parallel data is viable to determine sense distinctions, and if so, the ways in which this information might be used. Given the lack of large parallel texts across multiple languages, the study is necessarily limited; however, close examination of a small sample of parallel data can, as a first step, provide the basis and direction for more extensive studies. I have used parallel, aligned versions of George Orwell's Nineteen Eighty-Four (Erjavec and Ide, 1998) in five languages: English, Slovene, Estonian, Romanian, and Czech.[1] The study therefore involves languages from four language families (Germanic, Slavic, Finno-Ugrec, and Romance), as well as two languages from the same family (Czech and Slovene). Four ambiguous English words were considered in this study: hard, line, head, and country. Line and hard were chosen because they have served in various WSD studies to date (e.g., Leacock et al, 1993) and a corpus of occurrences of these words from the Wall Street Journal corpus was generously made available for comparison. Serve, another word frequently used in these studies, did not appear frequently enough in the Orwell text to be considered, nor did any other suitable ambiguous verb. Country and head were chosen as substitutes because they appeared frequently enough for consideration.

All sentences containing an occurrence or occurrences (including morphological variants) of each of the three words were extracted from the English text, together with the parallel sentences in which they occur in the texts of the four comparison languages (Czech, Estonian, Romanian, Slovene). The English occurrences were grouped into senses, using the relatively coarse sense distinctions in the Oxford Advanced Learner's Dictionary (OALD)[2] (used to provide sense distinctions in WordNet [Miller et al., 1990; Fellbaum, forthcoming]). The sense categorization was performed by the author and two student assistants; results from the three were compared and a final, mutually agreeable grouping was established.

For each of the four comparison languages, the corpus of sense-grouped parallel sentences for English and that language was sent to a linguist and native speaker of the comparison language. The linguists were asked to provide the following information for each word occurrence:

  1. Provide the lexical item in each parallel sentence that corresponds to the ambiguous English word. If it is inflected, provide both the inflected form and the root form.
  2. Is the translation one-to-one (i.e., the English word is translated by a single word in your language)? If not, please provide the phrase (or other means) by which it is translated, or indicate that it is not lexicalized.
  3. Are there obvious synonyms for the word in your language that could have been used instead of the one chosen? Are they better or worse as translations?
  4. If a given word in any one of its senses is translated using different words in your language (for example, if a word in the "not soft" sense of "hard" is translated differently in different sentences), please indicate why this difference may exist. For example, is it due to the use of a more general term (hyponym)? a more specific word (hypernym)? a different sense?
  5. Is any of the translations of one of the ambiguous words itself ambiguous in your language? Is the ambiguity the same as in the English? If not, is the word ambiguous among different meanings than those for which it is ambiguous in English? If so, what are its other meanings?

For over 85% of the English word occurrences, a specific lexical item or items could be identified as the translation equivalent for the corresponding English word.

In order to determine the degree to which the assigned sense distinctions from the OALD correspond to translation equivalents, a coherence index (CI) was computed that measures the consistency with which a given sense is translated as well as the degree of relationship between two senses. CIs were also computed for each language individually. A simple correlation was then run over all the CI data, providing an index of the degree to which there is an affinity (or disaffinity) between the different senses of a given word in each of these groups. Finally, in order to determine the degree to which the linguistic relation between languages may affect coherence, a correlation was run among CIs for all pairs of the four target languages.

The results, which will be fully outlined in the final paper, show that cross-lingual information may be useful for automatic disambiguation, especially for gross sense distinctions. More interestingly, the data suggest that translation equivalents may provide a valuable source of information for determining sense distinctions, by providing an indication of the relatedness between sense s of a given word that are derived from standard dictionaries. In particular, the CI's can be used to define a "map" depicting the relative distance between senses. This information can in turn serve as a basis for collapsing two senses when the cross-lingual data suggest that their meanings are nearly interchangeable or for recognizing them as relatively distinct. An even more promising approach for sense determination is to use information about translation equivalents to group word occurrences into sense clusters without assigning or considering senses defined a priori in a dictionary. We are exploring this last idea and will have additional results to report in the final paper.

Notes

  1. The Orwell parallel corpus also includes versions of Nineteen-Eighty Four in Hungarian, Bulgarian, Latvian, Lithuanian, Serbian, and Russian.

  2. Note that sense divisions for line and hard can be very fine in larger, standard dictionaries, often involving dozens of senses (e.g., in the Collins English Dictionary, line as a noun has 63 senses)

References

Dagan, Ido and Itai, Alon (1994). "Word sense disambiguation using a second language monolingual corpus." Computational Linguistics, 20(4), 563-596.

Dagan, Ido; Itai, Alon; and Schwall, Ulrike (1991). "Two languages are more informative than one." Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, 18-21 June 1991, Berkeley, California, 130-137.

Dyvik, Helge (1998). "Translations as Semantic Mirrors." Proceedings of Workshop W13: Multilinguality in the lexicon II, The 13th Biennial European Conference on Artificial Intelligence (ECAI 98), Brighton, UK, 24-44.

Erjavec, Tomaz and Ide, Nancy (1998). "The MULTEXT-EAST Corpus." Proceedings of the First International Conference on Language Resources and Evaluation, 27-30 May 1998, Granada, 971-74.

Fellbaum, Christiane (ed.) (forthcoming). WordNet: An Electronic Lexical Database. MIT Press, Cambridge, Massachusetts.

Gale, William A.; Church, Kenneth W. and Yarowsky, David (1993). "A method for disambiguating word senses in a large corpus." Computers and the Humanities, 26, 415-439.

Hearst, Marti A. (1991). "Noun homograph disambiguation using local context in large corpora." Proceedings of the 7th Annual Conference of the University of Waterloo Centre for the New OED and Text Research, Oxford, United Kingdom, 1-19.

Leacock, Claudia; Towell, Geoffrey and Voorhees, Ellen (1993). "Corpus-based statistical sense resolution." Proceedings of the ARPA Human Language Technology Workshop, San Francisco, Morgan Kaufman.

Melamed, I. Dan. (1997). "Measuring Semantic Entropy." ACL-SIGLEX Workshop Tagging Text with Lexical Semantics: Why, What, and How? April 4-5, 1997, Washington, D.C., 41-46.

Miller, George A.; Beckwith, Richard T. Fellbaum, Christiane D.; Gross, Derek and Miller, Katherine J. (1990). "WordNet: An on-line lexical database." International Journal of Lexicography, 3(4), 235-244.

Resnik, Philip and Yarowsky, David (1997b). "A perspective on word sense disambiguation methods and their evaluation." ACL-SIGLEX Workshop Tagging Text with Lexical Semantics: Why, What, and How? April 4-5, 1997, Washington, D.C., 79-86.

Schütze, Hinrich (1992). "Dimensions of meaning." Proceedings of Supercomputing '92. IEEE Computer Society Press, Los Alamitos, California, 787-796.

Schütze, Hinrich (1993). "Word space." Hanson, Stephen J.; Cowan, Jack D.; and Giles, C. Lee (Eds.) Advances in Neural Information Processing Systems 5, Morgan Kauffman, San Mateo, California, 5, 895-902.

Yarowsky, David (1992). "Word sense disambiguation using statistical models of Roget's categories trained on large corpora." Proceedings of the 14th International Conference on Computational Linguistics, COLING'92, 23-28 August, Nantes, France, 454-460.

Yarowsky, David (1993). "One sense per collocation." Proceedings of the ARPA Human Language Technology Workshop, Princeton, New Jersey, 266-271.