Collocations in NLP


Staff member
15. Collocations

Kathleen R. McKeown & Dragomir R. Radev. 2000. Collocations. In Robert Dale, Hermann Moisl & Harold Somers (eds.) A Handbook of Natural Language Processing.
Marcel Dekker.

This chapter describes a class of word groups that lies between idioms and free word combinations. Idiomatic expressions are those in which the semantics of the whole cannot be deduced from the meanings of the individual constituents. Free word combinations have the properties that each of the words can be replaced by another without seriously modifying the overall meaning of the composite unit and if one of the words is omitted, a reader cannot easily infer it from the remaining ones. Unlike free word combinations, a collocation is a group of words that occur together more often than by chance. On the other hand, unlike idioms, individual words in a collocation can contribute to the overall semantics of the compound. We present some definitions and examples of collocations, as well as methods for their extraction and classification. The use of collocations for word sense disambiguation, text generation, and machine translation is also part of this chapter.



Full bibliography information needed: The handbook of natural language processing is published by which publishing company, please?