Using WordNet in Extracting the Final Answer from Retrieved Documents in a Question Answering System

Abstract. In this project we propose a model for answer extraction component of a question answering system called SBUQA. Methods which extract answers based on only the keywords ignore many acceptable answers of the question. Therefore, in our proposed system we exploit methods for meaning extension of the question and the candidate answers and also make use of ontology (WordNet). In order to represent the question and the candidate answers and comparing them to each other, we use LFG- Lexical Functional Grammar, a meaning based grammar that analyses sentences in a deeper level than syntactic parsing- and obtain the f-structure of the sentences. We recognize the appropriate f-structure pattern of the question and based on that, the f-structure patterns of the answers. Then, the answer’s pattern is matched to the pattern of the candidate answer by the proposed matching method, called extended unification of f-structure. Finally, the sentences which acquire the minimum score to be offered the user are selected; the answer clause is identified in them and displayed to the user in descending order