Using Multiple Combined Ranker for answering definitional questions

This paper presents a Multiple Combined Ranker (MCR) approach for answering definitional questions. Generally, our MCR approach first extracts question target-related knowledge as much as possible, then using this knowledge to pick up appropriate question answers. The knowledge includes both online definitions and related terms (RT). In our system, extraction of related terms is different from traditional methods which are largely based on calculating the co-occurred frequency of target words. We adopted the significance of sentences and documents, from which RT were extracted. The MCR approach shows state-in-art performance in handling with increasingly complex definitional questions.