Paper Info
Title
Full machine translation for factoid question answering
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-Bonet14614.35
Pere Comas2827.23