Automatic Coupling of Answer Extraction and Information Retrieval

Xuchen Yao, Benjamin Van Durme, Peter Clark
2013 Annual Meeting of the Association for Computational Linguistics  
Information Retrieval (IR) and Answer Extraction are often designed as isolated or loosely connected components in Question Answering (QA), with repeated overengineering on IR, and not necessarily performance gain for QA. We propose to tightly integrate them by coupling automatically learned features for answer extraction 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
more » ... 0%-20% against an uncoupled retrieval baseline in both document and passage retrieval, which further leads to a downstream 20% improvement in QA F 1 .
dblp:conf/acl/YaoDC13 fatcat:ky4ctuof65edfj7ifhnubpa6wy