Date: 05 Feb 2002

Multiword Expressions: A Pain in the Neck for NLP

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Multiword expressions are a key problem for the development of large-scale, linguistically sound natural language processing technology. This paper surveys the problem and some currently available analytic techniques. The various kinds of multiword expressions should be analyzed in distinct ways, including listing “words with spaces”, hierarchically organized lexicons, restricted combinatoric rules, lexical selection, “idiomatic constructions” and simple statistical affinity. An adequate comprehensive analysis of multiword expressions must employ both symbolic and statistical techniques.

The research reported here was conducted in part under the auspices of the LinGO project, an international collaboration centered around the lkb system and related resources (see http://lingo.stanford.edu). This research was supported in part by the Research Collaboration between NTT Communication Science Laboratories, Nippon Telegraph and Telephone Corporation and CSLI, Stanford University. We would like to thank Emily Bender and Tom Wasow for their contributions to our thinking. However, we alone are responsible for any errors that remain.