Lei Zou
Jeffrey Xu Yu
ABSTRACT
RDF question/answering (Q/A) allows users to ask questions in natural languages over a knowledge base represented by RDF. To answer a national language question, the existing work takes a two-stage approach: question understanding and query evaluation. Their focus is on question understanding to deal with the disambiguation of the natural language phrases. The most common technique is the joint disambiguation, which has the exponential search space. In this paper, we propose a systematic framework to answer natural language questions over RDF repository (RDF Q/A) from a graph data-driven perspective. We propose a semantic query graph to model the query intention in the natural language question in a structural way, based on which, RDF Q/A is reduced to subgraph matching problem. More importantly, we resolve the ambiguity of natural language questions at the time when matches of query are found. The cost of disambiguation is saved if there are no matching found. We compare our method with some state-of-the-art RDF Q/A systems in the benchmark dataset. Extensive experiments confirm that our method not only improves the precision but also speeds up query performance greatly.
- Natural language question answering over rdf. In technique report, omitted due to the double-blind reviewing. Some materials are provided in our response document.Google Scholar
- I. Androutsopoulos and P. Malakasiotis. A survey of paraphrasing and textual entailment methods. J. Artif. Intell. Res. (JAIR), 38:135--187, 2010. Google ScholarDigital Library
- J. Berant, A. Chou, R. Frostig, and P. Liang. Semantic parsing on freebase from question-answer pairs. In EMNLP, pages 1533--1544, 2013.Google Scholar
- C. Bizer, J. Lehmann, G. Kobilarov, S. Auer, C. Becker, R. Cyganiak, and S. Hellmann. Dbpedia - a crystallization point for the web of data. J. Web Sem., 7(3):154--165, 2009. Google ScholarDigital Library
- D. M. Cer, M.-C. de Marneffe, D. Jurafsky, and C. D. Manning. Parsing to stanford dependencies: Trade-offs between speed and accuracy. In LREC, 2010.Google Scholar
- P. Cimiano, V. Lopez, C. Unger, E. Cabrio, A.-C. N. Ngomo, and S. Walter. Multilingual question answering over linked data (qald-3): Lab overview. In CLEF, pages 321--332, 2013.Google ScholarDigital Library
- L. P. Cordella, P. Foggia, C. Sansone, and M. Vento. A (sub)graph isomorphism algorithm for matching large graphs. IEEE Trans. Pattern Anal. Mach. Intell., 26(10):1367--1372, 2004. Google ScholarDigital Library
- M.-C. de Marneffe and C. D. Manning. Stanford typed dependencies manual.Google Scholar
- J. Eisner. Three new probabilistic models for dependency parsing: An exploration. In COLING, pages 340--345, 1996. Google ScholarDigital Library
- A. Fader, S. Soderland, and O. Etzioni. Identifying relations for open information extraction. In EMNLP, pages 1535--1545, 2011. Google ScholarDigital Library
- R. Fagin, A. Lotem, and M. Naor. Optimal aggregation algorithms for middleware. In PODS, pages 102--113, 2001. Google ScholarDigital Library
- G. Ladwig and T. Tran. Combining query translation with query answering for efficient keyword search. In ESWC (2), pages 288--303, 2010. Google ScholarDigital Library
- V. Lopez, C. Unger, P. Cimiano, and E. Motta. Evaluating question answering over linked data. J. Web Sem., 21:3--13, 2013. Google ScholarDigital Library
- K. Losemann and W. Martens. The complexity of regular expressions and property paths in sparql. ACM Trans. Database Syst., 38(4):24, 2013. Google ScholarDigital Library
- C. D. Manning, P. Raghavan, and H. Schütze. Introduction to Information Retrieval. Cambridge University Press, New York, 2008. Google ScholarDigital Library
- R. Mihalcea and A. Csomai. Wikify!: linking documents to encyclopedic knowledge. In CIKM, pages 233--242, 2007. Google ScholarDigital Library
- N. Nakashole, G. Weikum, and F. M. Suchanek. Discovering and exploring relations on the web. PVLDB, 5(12):1982--1985, 2012. Google ScholarDigital Library
- N. Nakashole, G. Weikum, and F. M. Suchanek. Patty: A taxonomy of relational patterns with semantic types. In EMNLP-CoNLL, pages 1135--1145, 2012. Google ScholarDigital Library
- A.-M. Popescu, O. Etzioni, and H. Kautz. Towards a theory of natural language interfaces to databases. In Proceedings of the 8th international conference on Intelligent user interfaces, pages 149--157. ACM, 2003. Google ScholarDigital Library
- D. R. Radev, H. Qi, Z. Zheng, S. Blair-Goldensohn, Z. Zhang, W. Fan, and J. M. Prager. Mining the web for answers to natural language questions. In CIKM, pages 143--150, 2001. Google ScholarDigital Library
- L.-A. Ratinov, D. Roth, D. Downey, and M. Anderson. Local and global algorithms for disambiguation to wikipedia. In ACL, pages 1375--1384, 2011. Google ScholarDigital Library
- D. Ravichandran and E. Hovy. Learning surface text patterns for a question answering system. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL '02, pages 41--47, 2002. Google ScholarDigital Library
- U. Sawant and S. Chakrabarti. Learning joint query interpretation and response ranking. In WWW, pages 1099--1110, 2013. Google ScholarDigital Library
- R. F. Simmons. Natural language question-answering systems: 1969. Commun. ACM, 13(1):15--30, Jan. 1970. Google ScholarDigital Library
- W. M. Soon, H. T. Ng, and D. C. Y. Lim. A machine learning approach to coreference resolution of noun phrases. Comput. Linguist., 27(4):521--544, 2001. Google ScholarCross Ref
- Z. Sun, H. Wang, H. Wang, B. Shao, and J. Li. Efficient subgraph matching on billion node graphs. PVLDB, 5(9):788--799, 2012. Google ScholarDigital Library
- C. Unger, L. Bühmann, J. Lehmann, A.-C. N. Ngomo, D. Gerber, and P. Cimiano. Template-based question answering over rdf data. In WWW, pages 639--648, 2012. Google ScholarDigital Library
- Y. Wu, C. Hori, H. Kawai, and H. Kashioka. Answering complex questions via exploiting social q&a collection. In IJCNLP, pages 956--964, 2011.Google Scholar
- M. Yahya, K. Berberich, S. Elbassuoni, M. Ramanath, V. Tresp, and G. Weikum. Natural language questions for the web of data. In EMNLP-CoNLL, pages 379--390, 2012. Google ScholarDigital Library
- M. Yahya, K. Berberich, S. Elbassuoni, and G. Weikum. Robust question answering over the web of linked data. In CIKM, pages 1107--1116, 2013. Google ScholarDigital Library
- W. Zhang, J. Su, C. L. Tan, and W. Wang. Entity linking leveraging automatically generated annotation. In COLING, pages 1290--1298, 2010. Google ScholarDigital Library
- P. Zhao and J. Han. On graph query optimization in large networks. PVLDB, 3(1):340--351, 2010. Google ScholarDigital Library
- L. Zou, J. Mo, L. Chen, M. T. Özsu, and D. Zhao. gstore: Answering sparql queries via subgraph matching. PVLDB, 4(8):482--493, 2011. Google ScholarDigital Library
Index Terms
- Natural language question answering over RDF: a graph data driven approach
Recommendations
Improving the Precision of RDF Question/Answering Systems: A Why Not Approach
WWW '17 Companion: Proceedings of the 26th International Conference on World Wide Web CompanionGiven a natural language question qNL over an RDF dataset D, an RDF Question/Answering (Q/A) system first translatesqNL into a SPARQL query graph Q and then evaluates Q over the underlying knowledge graph to figure out the answers Q(D). However, due to ...
Natural language question answering over RDF data
SIGMOD '13: Proceedings of the 2013 ACM SIGMOD International Conference on Management of DataAs more and more RDF data becomes available, such as DBpedia, Yago and Freebase, it is desired to provide users with simple interfaces to access the datasets. Although the SPARQL query language is a standard way to query RDF data, it remains tedious and ...
A Semantic Similarity-based Subgraph Matching Method for Improving Question Answering over RDF
WWW '20: Companion Proceedings of the Web Conference 2020RDF question/answering (Q/A) system can explore RDF data by translating natural language questions into SPARQL queries. In this poster, we design a generation-and-ranking approach to translate natural language questions into SPARQL queries based on ...
Comments