Hot-spot passage retrieval in question answering

Question Answering has been the recent focus of information retrieval research; many systems just incorporate a search engine as a black box and most effort has been devoted to the question analyzer and the answer identifier. In the context of QA, however, passage provides an ideal medium between the document collection and an exact answer. And passage retrieval is a finer-grain approach than the traditional document retrieval both for the answer identifier and a human reader. In this paper, distinctions are first made between document retrieval and passage retrieval. And the Hot-Spot Passage Retrieval algorithm, which takes into account the measures of blurred BM25, coverage and height, is examined in detail. For evaluation, an isolated test is conducted and the algorithm gains 18.3% better answer redundancy and 4.8% better coverage rate than Okapi's original passage retrieval algorithm.