Using Recognizing Textual Entailment as a Core Engine for Answer Validation

Abstract. This paper is about our approach to answer validation, which centered by a Recognizing Textual Entailment (RTE) core engine. We first combined the question and the answer into Hypothesis (H) and view the document as Text (T); then, we used our RTE system to check whether the entailment relation holds between them. Our system was evaluated on the Answer Validation Exercise (AVE) task and achieved f-measures of 0.46 and 0.55 for two submission runs, which both outperformed others ’ results for the English language. 1 Introduction and Related Work Question Answering (QA) is an important task in Natural Language Processing (NLP), which aims to mine answers to natural language questions from large corpora. Answer validation (AV) is to evaluate the answers obtained by the former stages of a QA system and select the most proper answers for the final output