Paper: Automatic Coupling of Answer Extraction and Information Retrieval

ACL ID P13-2029
Title Automatic Coupling of Answer Extraction and Information Retrieval
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

Information Retrieval (IR) and Answer Extraction are often designed as isolated or loosely connected components in Ques- tion Answering (QA), with repeated over- engineering on IR, and not necessarily per- formance gain for QA. We propose to tightly integrate them by coupling auto- matically learned features for answer ex- traction to a shallow-structured IR model. Our method is very quick to implement, and significantly improves IR for QA (measured in Mean Average Precision and Mean Reciprocal Rank) by 10%-20% against an uncoupled retrieval baseline in both document and passage retrieval, which further leads to a downstream 20% improvement in QA F1.