Building a Rich Large-scale Lexical Base for Generation

Jing, Hongyan; McKeown, Kathleen; Passonneau, Rebecca J.

Most large lexical resources have been developed with language interpretation in mind and can not be used directly for generation. we present a rich large-scale lexical base for generation, constructed by merging various linguistic resources. Our approach meets the needs of language generation systems by providing the facilities for mapping from semantic concepts to verb/sense pairs, for identifying the valid subcategorization forms for a given verb sense, and for representing alternations for paraphrasing power. Information from different resources enriches and constrains each other, so the final result is complete as well as accurate. We show by example how this lexical base can be integrated into a generation package and how it simplifies development process while improving system performance.



More About This Work

Academic Units
Computer Science
Department of Computer Science, Columbia University
Columbia University Computer Science Technical Reports, CUCS-016-97
Published Here
April 25, 2011