Exploiting Lexical Regularities in Designing Natural Language Systems.
Abstract
This paper presents the lexical component of the START Question Answering system developed at the MIT Artificial Intelligence Lab. START is able to interpret correctly a wide range of semantic relationships associated with alternate expressions of the arguments of verbs. The design of the system takes advantage of the results of recent linguistic research into the structure of the lexicon, allowing START to attain a broader range of coverage than many existing systems. It is concluded that the addition of a component that explicitly encodes verb classes and their characteristic properties, enables the START system to handle a wide range of phenomena reflecting semantic-syntactic correspondences that are characteristic of English verbs. By factoring properties that belong to whole classes of verbs out of the entries of individual verbs and letting these entries simply designate the verb's class membership, we do more than merely simplify entries. We facilitate the addition of new words to the lexicon and make it easier to extend the system's coverage of linguistic phenomena. Keywords: Diathesis alternations; Verb classes. (edc)
Document Details
- Document Type
- Technical Report
- Publication Date
- Apr 01, 1988
- Accession Number
- ADA195922
Entities
People
- Beth Levin
- Boris Katz
Organizations
- Massachusetts Institute of Technology