Paper: Learning Named Entity Hyponyms for Question Answering

ACL ID I08-2112
Title Learning Named Entity Hyponyms for Question Answering
Venue International Joint Conference on Natural Language Processing
Session Main Conference
Year 2008
Authors

Lexical mismatch is a problem that con- founds automatic question answering sys- tems. While existing lexical ontologies such as WordNet have been successfully used to match verbal synonyms (e.g., beat and de- feat) and common nouns (tennis is-a sport), their coverage of proper nouns is less ex- tensive. Question answering depends sub- stantially on processing named entities, and thus it would be of significant benefit if lexical ontologies could be enhanced with additional hypernymic (i.e., is-a) relations that include proper nouns, such as Edward Teach is-a pirate. We demonstrate how a re- cently developed statistical approach to min- ing such relations can be tailored to iden- tify named entity hyponyms, and how as a result, superior question answering perfor- mance can be obtained. We ...