Acquiring New Words from Context

Issue title: Knowledge Extraction from Text

Guest editors: Steven L. LytinenGuest Editor

Article type: Research Article

Authors: Lytinen, Steven L.^{; *} | Hastings, Peter M.

Affiliations: Artificial Intelligence Laboratory, The University of Michigan, Ann Arbor, Michigan 48109

Correspondence: [*] To whom all correspondence should be addressed.

Abstract: We present an incremental approach to the task of learning word definitions, including both syntactic and semantic information, from the use of unknown words in context. It is implemented in a unification-based natural language system called LINK. The approach naturally fits into LINK's normal language processing. Unification operations, applied routinely during processing, provide the learning algorithm with both syntactic and semantic information, which it uses to formulate hypotheses about word definitions. We describe the LINK system and the learning algorithm, and present the results of an empirical test, in which the algorithm was used on a limited-domain application corpus.

DOI: 10.3233/ICA-1994-1604

Journal: Integrated Computer-Aided Engineering, vol. 1, no. 6, pp. 511-526, 1994