Answer Validation for Question Answering Systems by Using External Resources

This paper focuses on extracting question-answer pairs on the Internet which is an useful resource for building Automated Question Answering systems. Question-answer pairs from public resources usually contain noisy information, mostly in the answers. Therefore to obtain reliable question-answer pairs, the answers need to be validated. Previous studies usually handled this problem based on the relationship between a question and its corresponding answers. Differently, this paper proposes a new approach that uses external resources to validate the reliability of answers from question-answer pairs crawled from the Web. We will combine both kinds of information, one is the matching between question and its answers while the other is based on the supporting of external resources to the answers. The experiment conducted on the question-answer pairs extracted from Yahoo!Answer and StackOverflow shows the effectiveness of our proposed method.

[1]  Ryuichiro Higashinaka,et al.  Corpus-based Question Answering for why-Questions , 2008, IJCNLP.

[2]  Lei Yu,et al.  Deep Learning for Answer Sentence Selection , 2014, ArXiv.

[3]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[4]  Kai H. Lim,et al.  Contributing high quantity and quality knowledge to online Q&A communities , 2013, J. Assoc. Inf. Sci. Technol..

[5]  Xuanjing Huang,et al.  Answering Definition Questions Using Web Knowledge Bases , 2005, IJCNLP.

[6]  Eric Brill,et al.  Automatic question answering using the web: Beyond the Factoid , 2006, Information Retrieval.

[7]  Yang Xiang,et al.  ICRC-HIT: A Deep Learning based Comment Sequence Labeling System for Answer Selection Challenge , 2015, *SEMEVAL.

[8]  Lin Sun,et al.  Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities , 2010, ACL.

[9]  Quan Hung Tran,et al.  JAIST: Combining multiple features for Answer Selection in Community Question Answering , 2015, *SEMEVAL.

[10]  Guy Shani,et al.  A Survey of Accuracy Evaluation Metrics of Recommendation Tasks , 2009, J. Mach. Learn. Res..

[11]  Eugene Agichtein,et al.  Finding the right facts in the crowd: factoid question answering over social media , 2008, WWW.

[12]  Jeffrey Pomerantz,et al.  Evaluating and predicting answer quality in community QA , 2010, SIGIR.

[13]  Yonatan Belinkov,et al.  VectorSLU: A Continuous Word Vector Approach to Answer Selection in Community Question Answering Systems , 2015, *SEMEVAL.

[14]  Ming Liu,et al.  Multimodal DBN for Predicting High-Quality Answers in cQA portals , 2013, ACL.

[15]  Tat-Seng Chua,et al.  Discovering high quality answers in community question answering archives using a hierarchy of classifiers , 2014, Inf. Sci..

[16]  Galia Angelova,et al.  Voltron: A Hybrid System For Answer Validation Based On Lexical And Distance Features , 2015, SemEval@NAACL-HLT.