Paper: Restoring an Elided Entry Word in a Sentence for Encyclopedia QA System

ACL ID I05-2037
Title Restoring an Elided Entry Word in a Sentence for Encyclopedia QA System
Venue International Joint Conference on Natural Language Processing
Session poster-demo-tutorial
Year 2005
Authors

This paper presents a hybrid model for restoring an elided entry word for en- cyclopedia QA system. In Korean en- cyclopedia, an entry word is frequently omitted in a sentence. If the QA system uses a sentence without an entry word, it cannot provide a right answer. For resolving this problem, we combine a rule-based approach with Maximum Entropy model to use the merit of each approach. A rule-based approach uses caseframes and sense classes. The re- sult shows that combined approach gives a 20% increase over our baseline.