Cluster-Based Selection of Statistical Answering Strategies
Lucian V Lita, Jaime Carbonell
Question answering (QA) is a highly complex task that brings together classification, clustering, retrieval, and extraction. Question answering systems include various statistical and rule-based components that combine and form multiple strategies for finding answers. However, in real-life scenarios efficiency constraints make it infeasible to simultaneously use all available strategies in a QA system. To address this issue, we present an approach for carefully selecting answering strategies that are likely to benefit individual questions, without significantly reducing performance. We evaluate the impact of strategy selection on question answering performance at several important QA stages: document retrieval, answer extraction, and answer merging. We present strategy selection experiments using a statistical question answering system, and we show significant efficiency improvements. By selecting 10% of the available answering strategies, we obtained similar performance when compared to using all of the strategies combined.