Denis Savenkov
ABSTRACT
One of the major challenges for automated question answering over Knowledge Bases (KBQA) is translating a natural language question to the Knowledge Base (KB) entities and predicates. Previous systems have used a limited amount of training data to learn a lexicon that is later used for question answering. This approach does not make use of other potentially relevant text data, outside the KB, which could supplement the available information. We introduce a new system, Text2KB, that enriches question answering over a knowledge base by using external text data. Specifically, we revisit different phases in the KBQA process and demonstrate that text resources improve question interpretation, candidate generation and ranking. Building on a state-of-the-art traditional KBQA system, Text2KB utilizes web search results, community question answering and general text document collection data, to detect question topic entities, map question phrases to KB predicates, and to enrich the features of the candidates derived from the KB. Text2KB significantly improves performance over the baseline KBQA method, as measured on a popular WebQuestions dataset. The results and insights developed in this work can guide future efforts on combining textual and structured KB data for question answering.
- S. Auer, C. Bizer, G. Kobilarov, J. Lehmann, R. Cyganiak, and Z. Ives. Dbpedia: A nucleus for a web of open data. Springer, 2007.Google Scholar
- K. Barker. Combining structured and unstructured knowledge sources for question answering in watson. In DILS, Lecture Notes in Computer Science. Springer, 2012. Google ScholarDigital Library
- H. Bast and E. Haussmann. More accurate question answering on freebase. Proceedings of CIKM, 2015. Google ScholarDigital Library
- P. Baudiš. Systems and approaches for question answering. 2015.Google Scholar
- P. Baudiš and J. Šediỳ. Modeling of the question answering task in the yodaqa system. In Experimental IR Meets Multilinguality, Multimodality, and Interaction. Springer, 2015. Google ScholarDigital Library
- J. Berant, A. Chou, R. Frostig, and P. Liang. Semantic parsing on freebase from question-answer pairs. In Proceedings of EMNLP, 2013.Google Scholar
- J. Berant and P. Liang. Semantic parsing via paraphrasing. In Proceedings of ACL, 2014.Google ScholarCross Ref
- J. Berant and P. Liang. Imitation learning of agenda-based semantic parsers. Transactions of the Association for Computational Linguistics, 3, 2015.Google Scholar
- K. Bollacker, C. Evans, P. Paritosh, T. Sturge, and J. Taylor. Freebase: A collaboratively created graph database for structuring human knowledge. In Proceedings of ICMD, 2008. Google ScholarDigital Library
- A. Bordes, S. Chopra, and J. Weston. Question answering with subgraph embeddings. In Proceedings of EMNLP, 2014.Google ScholarCross Ref
- E. Brill, S. Dumais, and M. Banko. An analysis of the askmsr question-answering system. In Proceedings of EMNLP. Association for Computational Linguistics, 2002. Google ScholarDigital Library
- M. Cornolti, P. Ferragina, M. Ciaramita, H. Schütze, and S. Rüd. The smaph system for query entity recognition and disambiguation. In Proceedings of the First International Workshop on Entity Recognition and Disambiguation, 2014. Google ScholarDigital Library
- J. Dalton. Entity-based Enrichment for Information Extraction and Retrieval. PhD thesis, University of Massachusetts Amherst, 2014.Google Scholar
- H. T. Dang, D. Kelly, and J. J. Lin. Overview of the trec 2007 question answering track. In Proceedings of TREC, 2007.Google Scholar
- A. Fader, S. Soderland, and O. Etzioni. Identifying relations for open information extraction. In Proceedings of EMNLP, 2011. Google ScholarDigital Library
- A. Fader, L. Zettlemoyer, and O. Etzioni. Open question answering over curated and extracted knowledge bases. In Proceedings of SIGKDD, 2014. Google ScholarDigital Library
- J. Lin. An exploration of the principles underlying redundancy-based factoid question answering. Transactions of ACM, 25(2), Apr. 2007. Google ScholarDigital Library
- M. Mintz, S. Bills, R. Snow, and D. Jurafsky. Distant supervision for relation extraction without labeled data. In Proceedings of ACL, 2009. Google ScholarDigital Library
- J. Pound, P. Mika, and H. Zaragoza. Ad-hoc object retrieval in the web of data. In Proceedings of WWW, 2010. Google ScholarDigital Library
- D. Savenkov, W.-L. Lu, J. Dalton, and E. Agichtein. Relation extraction from community generated question-answer pairs. In Proceedings of NAACL: Student Research Workshop, 2015.Google ScholarCross Ref
- V. I. Spitkovsky and A. X. Chang. A cross-lingual dictionary for english wikipedia concepts. In Proceedings of LREC, 2012.Google Scholar
- H. Sun, H. Ma, W.-t. Yih, C.-T. Tsai, J. Liu, and M.-W. Chang. Open domain question answering via semantic enrichment. Proceedings of WWW, 2015. Google ScholarDigital Library
- C. Unger, C. Forascu, V. Lopez, A.-C. N. Ngomo, E. Cabrio, P. Cimiano, and S. Walter. Question answering over linked data (qald-5). In Proceedings of CLEF, 2015.Google Scholar
- D. Vrandečić and M. Krötzsch. Wikidata: A free collaborative knowledgebase. Communications of ACM, (10), Sept. 2014. Google ScholarDigital Library
- K. Xu, Y. Feng, S. Reddy, S. Huang, and D. Zhao. Enhancing freebase question answering using textual evidence. arXiv preprint arXiv:1603.00957, 2016.Google Scholar
- M. Yahya, D. Barbosa, K. Berberich, Q. Wang, and G. Weikum. Relationship queries on extended knowledge graphs. In Proceedings of WSDM, 2016. Google ScholarDigital Library
- M. Yahya, K. Berberich, S. Elbassuoni, and G. Weikum. Robust question answering over the web of linked data. In Proceedings of the CIKM, 2013. Google ScholarDigital Library
- X. Yao. Lean question answering over freebase from scratch. In Proceedings of NAACL Demo, 2015.Google ScholarCross Ref
- X. Yao, J. Berant, and B. Van Durme. Freebase qa: Information extraction or semantic parsing? In Proceedings of ACL, 2014.Google ScholarCross Ref
- X. Yao and B. Van Durme. Information extraction over structured data: Question answering with freebase. In Proceedings of ACL, 2014.Google ScholarCross Ref
- W.-t. Yih, M.-W. Chang, X. He, and J. Gao. Semantic parsing via staged query graph generation: Question answering with knowledge base. In Proceedings of ACL, 2015.Google ScholarCross Ref
Index Terms
- When a Knowledge Base Is Not Enough: Question Answering over Knowledge Bases with External Text Data
Recommendations
Table Cell Search for Question Answering
WWW '16: Proceedings of the 25th International Conference on World Wide WebTables are pervasive on the Web. Informative web tables range across a large variety of topics, which can naturally serve as a significant resource to satisfy user information needs. Driven by such observations, in this paper, we investigate an ...
Question Answering When Knowledge Bases are Incomplete
Experimental IR Meets Multilinguality, Multimodality, and InteractionAbstractWhile systems for question answering over knowledge bases (KB) continue to progress, real world usage requires systems that are robust to incomplete KBs. Dependence on the closed world assumption is highly problematic, as in many practical cases ...
Open Domain Question Answering via Semantic Enrichment
WWW '15: Proceedings of the 24th International Conference on World Wide WebMost recent question answering (QA) systems query large-scale knowledge bases (KBs) to answer a question, after parsing and transforming natural language questions to KBs-executable forms (e.g., logical forms). As a well-known fact, KBs are far from ...
Comments