Experiments on Extracting Knowledge from a Machine-Readable Dictionary of Synonym Differences

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2004)


In machine translation and natural language generation, making the wrong word choice from a set of near-synonyms can be imprecise or awkward, or convey unwanted implications. Using Edmonds’s model of lexical knowledge to represent clusters of near-synonyms, our goal is to automatically derive a lexi- cal knowledge-base from the Choose the Right Word dictionary of near-synonym discrimination. We do this by automatically classifying sentences in this dictio- nary according to the classes of distinctions they express. We use a decision-list learning algorithm to learn words and expressions that characterize the classes DENOTATIONAL DISTINCTIONS and ATTITUDE-STYLE DISTINCTIONS. These results are then used by an extraction module to actually extract knowledge from each sentence. We also integrate a module to resolve anaphors and word-to-word comparisons. We evaluate the results of our algorithm for several randomly se- lected clusters against a manually built standard solution, and compare them with the results of a baseline algorithm.


Machine Translation Word Sense Disambiguation Class Hierarchy Baseline Algorithm Lexical Knowledge 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1996]
    Abney, Steven: Partial parsing via finite-state cascades. Proceedings of the ESSLLI’ 96 Robust Parsing Workshop (1996)Google Scholar
  2. [1997]
    Charniak, Eugene: Statistical techniques for natural language parsing. AI Magazine 18(4) (1997) 33–44Google Scholar
  3. [1999]
    Collins, Michael and Singer, Yoram: Unsupervised models for named entity classification. In Proceedings of Empirical Methods in Natural Language Processing and Very Large Corpora (EMNLP/VLC-99) (1999)Google Scholar
  4. [1993]
    DiMarco, Chrysanne, Hirst, Graeme and Stede, Manfred: The semantic and stylistic differentiation of synonyms and near-synonyms. Proceedings of AAAI Spring Symposium on Building Lexicons for Machine Translation, Stanford, CA (1993) 114–121Google Scholar
  5. [1993]
    DiMarco, Chrysanne and Hirst, Graeme: Usage notes as the basis for a representation of near-synonymy for lexical choice. Proceedings of 9th annual conference of the University of Waterloo Centre for the New Oxford English Dictionary and Text Research (1993) 33–43Google Scholar
  6. [1999]
    Edmonds, Philip: Semantic representations of near-synonyms for automatic lexical choice. Ph.D Thesis, University of Toronto (1999)Google Scholar
  7. [2000]
    Edmonds, Philip and Hirst, Graeme: Reconciling fine-grained lexical knowledge and coarse-grained ontologies in the representation of near-synonyms. In Proceedings of the Workshop on Semantic Approximation, Granularity, and Vagueness, Breckenridge, Colorado (2000)Google Scholar
  8. [1984]
    Gove, P.B. (ed.): Webster’s New Dictionary of Synonyms. G.&C. Merriam Co. (1984)Google Scholar
  9. [1994]
    Hayakawa, S.I., Ehrlich Eugene (revising ed.): Choose the Right Word. HarperCollins Publishers, Second edition (1994)Google Scholar
  10. [1995]
    Hirst, Graeme: Near-synonymy and the structure of lexical knowledge. Working notes, AAAI Symposium on Representation and Acquisition of Lexical Knowledge: Polysemy, Ambiguity, and Generativity, Stanford University (1995) 51–56Google Scholar
  11. [1990]
    Hovy, Eduard: Pragmatics and language generation. Artificial Intelligence, 43 (1990) 153–197CrossRefGoogle Scholar
  12. [1999]
    Riloff, Ellen and Jones, Rosie: Learning dictionaries for information-extraction by multilevel bootstrapping. In Proceedings of the Sixteenth Conference on Artificial Intelligence (AAAI-99) (1999) 474–479Google Scholar
  13. [1995]
    Yarowsky, David: Unsupervised word sense disambiguation rivaling supervised methods. In Proceedings of the 33rd AnnualMeeting of the Association for Computational Linguistics. Cambridge, MA (1995) 189–196Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2001

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of TorontoTorontoCanada

Personalised recommendations