Elamur Research⌕
☰
home / papers / 2013 / Computing Lexical Contrast

Computing Lexical Contrast

Paper · 2013 · Saif M. Mohammad, Bonnie J. Dorr, Graeme Hirst et al.

Summary

Applications such as machine translation, information retrieval, contradiction detection and dialogue systems benefit from knowing how strongly two words contrast in meaning. Hand-built lexicons, however, mostly list classic opposites (hot/cold), rarely say what kind of opposite a pair is, and leave out weaker contrasting pairs like tropical/freezing. Mohammad, Dorr, Hirst and Turney propose an automatic measure built on a "contrast hypothesis": two words contrast if each is closely related to one member of some pair of opposites. Seed opposites, partly obtained through affix patterns, are combined with the category structure of the Roget-like Macquarie Thesaurus to find contrasting categories. Corpus co-occurrence then grades the degree of contrast, since opposites appear together more often than chance would predict. A large Mechanical Turk study also measures how reliably people recognize opposites and their kinds. The method was tested on four data sets and two tasks: GRE-style "most contrasting word" questions and telling synonyms from opposites. It achieves high precision and broad coverage and outperforms earlier approaches. The released lexicons and data form a reusable resource.

Key points

  • Of the opposing word pairs that appear in GRE questions asking for the most contrasting word, more than 90% are missing from WordNet's antonymy links, which shows how limited manual lexicons are.
  • Crowd annotators agree strongly on what counts as an opposite, but agreement differs by kind of opposite, and many pairs show traits of several kinds.
  • Contrasting pairs co-occur in text far more often than random pairs or near-synonyms, though the large variance means co-occurrence alone cannot separate them from synonyms.
  • Results are broken down across four parts of speech and five kinds of opposites. Evaluation data include 162 development and 790 test GRE questions plus 1,269 newly created questions.
  • Released resources include 15 affix rules, 12,448 crowdsourced assignments, 209 manually identified contrasting category pairs in the Macquarie Thesaurus, and generated lexicons of 3.5M (Class I) and 2.5M (Class II) word pairs.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of Maryland, College ParkCollege Park · United States132 works · 25,380 citations🎓University of TorontoToronto · Canada96 works · 142,007 citations🏛️National Research Council CanadaOttawa · Canada59 works · 21,677 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

Cite

Cite as Saif M. Mohammad, Bonnie J. Dorr, Graeme Hirst and Peter D. Turney. 2013. Computing Lexical Contrast. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00143

@article{mohammad2013computing,
  title = {{Computing Lexical Contrast}},
  author = {Saif M. Mohammad, Bonnie J. Dorr, Graeme Hirst and Peter D. Turney},
  journal = {Computational Linguistics},
  year = {2013},
  doi = {10.1162/coli\_a\_00143},
  url = {https://doi.org/10.1162/coli_a_00143}
}

References

48 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Agresti, Alan. 1990. Categorical Data Analysis. Wiley, New York, NY. find
  2. Banerjee, Satanjeev and Ted Pedersen. 2003. Extended gloss overlaps as a measure of semantic relatedness. In International Joint Conference on Artificial Intelligence, pages 805–810, Acapulco, Mexico.
  3. Bejar, Isaac I., Roger Chaffin, and Susan Embretson. 1991. Cognitive and Psychometric Analysis of Analogical Problem Solving. Springer-Verlag, New York. find
  4. Brants, Thorsten and Alex Franz. 2006. Web 1T 5-gram version 1. Linguistic Data Consortium, Philadelphia, PA. find
  5. Budanitsky, Alexander and Graeme Hirst. 2006. Evaluating WordNet-based measures of semantic distance. Computational Linguistics, 32(1):13–47. find
  6. Burnard, Lou. 2000. Reference Guide for the British National Corpus (World Edition). Oxford University Computing Services, Oxford. find
  7. Charles, Walter G. and George A. Miller. 1989. Contexts of antonymous adjectives. Applied Psychology, 10:357–375. find
  8. Church, Kenneth and Patrick Hanks. 1990. Word association norms, mutual information and lexicography. Computational Linguistics, 16(1):22–29.
  9. Cruse, David A. 1986. Lexical Semantics. Cambridge University Press, Cambridge. find
  10. Curran, James R. 2004. From Distributional to Semantic Similarity. Ph.D. thesis, School of Informatics, University of Edinburgh, Edinburgh, UK. de Marneffe, Marie-Catherine, Anna Rafferty, and Christopher D. Manning. 2008. Finding contradictions in text. In Proceedings of the 46th Annual Meeting of…
  11. Deese, James. 1965. The Structure of Associations in Language and Thought. The Johns Hopkins University Press, Baltimore, MD. find
  12. Egan, Rose F. 1984. Survey of the history of English synonymy. Webster’s New Dictionary of Synonyms, pages 5a–25a. find
  13. Fellbaum, Christiane. 1995. Co-occurrence and antonymy. International Journal of Lexicography, 8:281–303. find
  14. Gross, Derek, Ute Fischer, and George A. Miller. 1989. Antonymy and the representation of adjectival meanings. Memory and Language, 28(1):92–106. find
  15. Harabagiu, Sanda M., Andrew Hickl, and Finley Lacatusu. 2006. Lacatusu: Negation, contrast and contradiction in text processing. In Proceedings of the 23rd National Conference on Artificial Intelligence (AAAI-06), pages 755–762, Boston, MA. find
  16. Hatzivassiloglou, Vasileios and Kathleen R. McKeown. 1997. Predicting the semantic orientation of adjectives. In Proceedings of the Eighth Conference on European Chapter of the Association for Computational Linguistics, pages 174–181, Madrid. find
  17. Hearst, Marti. 1992. Automatic acquisition of hyponyms from large text corpora. In Proceedings of the Fourteenth International Conference on Computational Linguistics, pages 539–546, Nantes.
  18. Jones, Steven, Carita Paradis, M. Lynne Murphy, and Caroline Willners. 2007. Googling for ‘opposites’: A Web-based study of antonym canonicity. Corpora, 2(2):129–154. find
  19. Justeson, John S. and Slava M. Katz. 1991. Co-occurrences of antonymous adjectives and their contexts. Computational Linguistics, 17:1–19.
  20. Kagan, Jerome. 1984. The Nature of the Child. Basic Books, New York. find
  21. Kay, Maire Weir, editor. 1988. Webster’s Collegiate Thesaurus. Merriam-Webster, Springfield, MA. find
  22. Kempson, Ruth M. 1977. Semantic Theory. Cambridge University Press, Cambridge. find
  23. Lehrer, Adrienne and K. Lehrer. 1982. Antonymy. Linguistics and Philosophy, 5:483–501. find
  24. Lin, Dekang. 1998. Automatic retrieval and clustering of similar words. In Proceedings of the 17th International Conference on Computational Linguistics, pages 768–773, Montreal.
  25. Lin, Dekang, Shaojun Zhao, Lijuan Qin, and Ming Zhou. 2003. Identifying synonyms among distributionally similar words. In Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI-03), pages 1,492–1,493, Acapulco. find
  26. Lobanova, Anna, Tom van der Kleij, and Jennifer Spenader. 2010. Defining antonymy: A corpus-based study of opposites by lexico-syntactic patterns. International Journal of Lexicography, 23(1):19–53. find
  27. Lucerto, Cupertino, David Pinto, and Héctor Jiménez-Salazar. 2002. An automatic method to identify antonymy. In Workshop on Lexical Resources and the Web for Word Sense Disambiguation, pages 105–111, Puebla. find
  28. Lyons, John. 1977. Semantics, volume 1. Cambridge University Press, Cambridge. find
  29. Marcu, Daniel and Abdesammad Echihabi. 2002. An unsupervised approach to recognizing discourse relations. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL-02), pages 368–375, Philadelphia, PA.
  30. Marton, Yuval, Ahmed El Kholy, and Nizar Habash. 2011. Filtering antonymous, trend-contrasting, and polarity-dissimilar distributional paraphrases for improving statistical machine translation. In Proceedings of the Sixth Workshop on Statistical Machine Translation, pages 237–249, Edinburgh. find
  31. McCarthy, Diana and Roberto Navigli. 2009. The English lexical substitution task. Language Resources And Evaluation, 43(2):139–159. find
  32. Mihalcea, Rada and Carlo Strapparava. 2005. Making computers laugh: Investigations in automatic humor recognition. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, pages 531–538, Vancouver.
  33. Mohammad, Saif, Bonnie Dorr, and Graeme Hirst. 2008. Computing word-pair antonymy. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP-2008), pages 982–991, Waikiki, HI. find
  34. Mohammad, Saif, Bonnie J. Dorr, Melissa Egan, Nitin Madnani, David Zajic, and Jimmy Lin. 2008. Multiple alternative sentence compressions and word-pair antonymy for automatic text summarization and recognizing textual entailment. In Text Analysis Conference (TAC), Gaithersburg, MD. find
  35. Mohammad, Saif, Cody Dunne, and Bonnie Dorr. 2009. Generating high-coverage semantic orientation lexicons from overtly marked words and a thesaurus. In Proceedings of Empirical Methods in Natural Language Processing (EMNLP-2009), pages 599–608, Singapore. find
  36. Mohammad, Saif, Iryna Gurevych, Graeme Hirst, and Torsten Zesch. 2007. Cross-lingual distributional profiles of concepts for measuring semantic distance. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP/CoNL… find
  37. Murphy, Gregory L. and Jane M. Andrew. 1993. The conceptual basis of antonymy and synonymy in adjectives. Journal of Memory and Language, 32(3):1–19. find
  38. Murphy, Lynne M. 2003. Semantic Relations and the Lexicon: Antonymy, Synonymy, and Other Paradigms. Cambridge University Press, Cambridge. find
  39. Murphy, Lynne M. and Steven Jones. 2008. Antonyms in children’s and child-directed speech. First Language, 28(4):403–430. find
  40. Pang, Bo and Lillian Lee. 2008. Opinion mining and sentiment analysis. find
  41. Foundations and Trends in Information Retrieval, 2(1–2):1–135. find
  42. Pang, Bo, Lillian Lee, and Shivakumar Vaithyanathan. 2002. Thumbs up?: Sentiment classification using machine learning techniques. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 79–86, Philadelphia, PA.
  43. Paradis, Carita, Caroline Willners, and Steven Jones. 2009. Good and bad opposites using textual and experimental techniques to measure antonym canonicity. The Mental Lexicon, 4(3):380–429. find
  44. Ploux, Sabine and Bernard Victorri. 1998. Construction d’espaces sémantiques à l’aide de dictionnaires de synonymes. TAL, 39(1):161–182. find
  45. Schwab, Didier, Mathieu Lafourcade, and Violaine Prince. 2002. Antonymy and conceptual vectors. In Proceedings of the 19th International Conference on Computational Linguistics (COLING-02), pages 904–910, Taipei, Taiwan. find
  46. Turney, Peter D. 2008. A uniform approach to analogies, synonyms, antonyms, and associations. In Proceedings of the 22nd International Conference on Computational Linguistics (COLING-08), pages 905–912, Manchester.
  47. Turney, Peter D. 2011. Analogy perception applied to seven tests of word comprehension. Journal of Experimental and Theoretical Artificial Intelligence - Psychometric Artificial Intelligence, 23(3):343–362. find
  48. Voorhees, Ellen M. 2008. Contradictions and justifications: Extensions to the textual entailment task. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL-08), 63–71, Columbus, OH.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/mohammad-2013-computing-lexical-contrast/