Розпізнавання багатослівних конструкцій

2011;
: pp. 158 – 165
Автори: 
Романюк А., Кваснюк Г., Романишин М.

Національний університет «Львівська політехніка»:

  • кафедра систем автоматизованого проектування;
  • кафедра прикладної лінгвістики.

This paper surveys the problem of multiword expressions (MWE), which plays the important role in development of large-scale, linguistically sound natural language processing technology. Multiword expressions are expressions which are made up of at least 2 words and which can be syntactically and/or semantically idiosyncratic. This category includes such constructions as compound nouns, idioms and phrasal verbs.This paper deals with modern approaches to MWE stratification, extraction and identification.

1. Baldwin T. An empirical model of multiword expressions decomposability. In Proc. of the ACL-2003 Workshop on Multiword Expressions: Analysis, Acquisition and Treatment / T. Baldwin, C. Bannard, T. Tanaka, D. Widdow. – 2003. 2. Baldwin T. Multiword Expressions (Presentation) / T. Baldwin. – Available from: www.csse.unimelb.edu.au/~tim/pubs/altss2004.pdf. 3. Church K. Word association norms, mutual information, and lexicography. Computational Linguistics / K. Church, P. Hanks. – 1990. 4. Dekang L. Automatic identification of non-compositional phrases. Proceedings of ACL-99 / L. Dekang. – 1999. 5. Dunning T. Accurate methods for the statistics of surprise and coincidence. Computational Linguistics / T. Dunning. – 1993. 6. Fellbaum C. WordNet: An Electronic Lexical Database / C. Fellbaum. – MIT Press, 1998. 7. Jurafsky D. Speech and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics and Speech Recognition / D. Jurafsky, J. H. Martin. – Upper Saddle River, NJ: Prentice Hall, 2008. – 988 p. – 2nd edition. 8.Katz G. Automatic identification of non-compositional multi-word expressions using latent semantic analysis. Proc. of the ACL-2006 Workshop on Multiword Expressions: Identifying and Exploiting Underlying Properties / G. Katz, E. Giesbrechts. – 2006. 9. McCarthy D. Detecting a continuum of compositionality in phrasal verbs. Proc. of the ACL-2003 Workshop on Multiword Expressions: Analysis, Acquisition and Treatment / D. McCarthy, B. Keller, J. Carroll. – 2003. 10. Moiron B. V. Identifying idiomatic expressions using automatic word alignment. Proceedings of the EACL 2006 Workshop on Multiword Expressions in a multilingual context / B. V. Moiron, J. Tiedemann. – 2006. 11. Sag I. Multiword expressions: A pain in the neck for nlp. Proceedings of CICLing / I. Sag, T. Baldwin, F. Bond, A. Copestake, D. Flickinger. – 2002. 12. Wray A. Formulaic Language and the Lexicon / A. Wray. – Cambridge University Press, 2002.