Simple Translation Models for Sentence Retrieval in Factoid Question Answering

Many question-answering systems start with a passage retrieval system to facilitate the answer extraction process. The richer the set of passages, in terms of answer content, the more accurate the answer extraction. We present a simple translation model for passage retrieval at the sentence level. We demonstrate this framework on TREC data, and show that it performs better than retrieval based on query likelihood, and on par with other systems.