Adaptive query-based model for improved ranking in closed domain factoid question answering

Abstract

The closed domain question answering QA systems achieve precision and recall at the cost of complex language processing techniques to parse the answer corpus. The task of locating the search phrase in the small answer corpus is non-trivial, as there are fewer answers to search from. We propose a query-based model for indexing answers in a closed domain factoid question answering system. Further, we use a phrase term inference method for improving the ranking order of related questions. Our solution offers an adaptive, lightweight approach to a factoid question answering system for domain specific knowledge bases with significantly simplified language processing techniques.