Full machine translation for factoid question answering
Document typeConference lecture
PublisherAssociation for Computational Linguistics
Rights accessOpen Access
In this paper we present an SMT-based approach to Question Answering (QA). QA is the task of extracting exact answers in response to natural language questions. In our approach, the answer is a translation of the question obtained with an SMT system. We use the n-best translations of a given question to find similar sentences in the document collection that contain the real answer. Although it is not the first time that SMT inspires a QA system, it is the first approach that uses a full Machine Translation system for generating answers. Our approach is validated with the datasets of the TREC QA evaluation.
CitationEspaña-Bonet, C.; Comas, P.R. Full machine translation for factoid question answering. A: Workshop on Exploiting Synergies between Information Retrieval and Machine Translation (ESIRMT) and Hybrid Approaches to Machine Translation (HyTra). "Joint workshop on Exploiting synergies between information retrieval and machine translation (ESIRMT) and Hybrid approaches to machine translation (HyTra) at EACL-2012: proceedings of the workshop". Avignon: Association for Computational Linguistics, 2012, p. 20-29.