Abstract | ||
---|---|---|
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. |
Year | Venue | Keywords |
---|---|---|
2012 | EACL 2012 Proceedings of the Joint Workshop on Exploiting Synergies between Information Retrieval and Machine Translation (ESIRMT) and Hybrid Approaches to Machine Translation (HyTra) | qa system,full machine translation system,document collection,trec qa evaluation,factoid question answering,natural language question,full machine translation,real answer,smt-based approach,exact answer,question answering,smt system |
Field | DocType | Citations |
Question answering,Information retrieval,Computer science,Machine translation,Machine translation system,Natural language,Natural language processing,Artificial intelligence,Factoid | Conference | 1 |
PageRank | References | Authors |
0.36 | 25 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Cristina España-Bonet | 1 | 46 | 14.35 |
Pere Comas | 2 | 82 | 7.23 |