Abstract
Multiple lines of research have developed Natural Language (NL) interfaces for formulating database queries. We build upon this work, but focus on presenting a highly detailed form of the answers in NL. The answers that we present are importantly based on the provenance of tuples in the query result, detailing not only the results but also their explanations. We develop a novel method for transforming provenance information to NL, by leveraging the original NL query structure. Furthermore, since provenance information is typically large and complex, we present two solutions for its effective presentation as NL text: one that is based on provenance factorization, with novel desiderata relevant to the NL case, and one that is based on summarization.
- E. Ainy, P. Bourhis, S. B. Davidson, D. Deutch, and T. Milo. Approximated summarization of data provenance. In CIKM, pages 483-492, 2015. Google ScholarDigital Library
- Y. Amsterdamer, A. Kukliansky, and T. Milo. A natural language interface for querying general and individual knowledge. VLDB, pages 1430-1441, 2015.Google Scholar
- P. Brgisser, M. Clausen, and M. A. Shokrollahi. Algebraic Complexity Theory. Springer Publishing Company, Incorporated, 2010. Google ScholarDigital Library
- A. P. Chapman, H. V. Jagadish, and P. Ramanan. Efficient provenance storage. In SIGMOD, pages 993-1006, 2008. Google ScholarDigital Library
- S. Cohen-Boulakia, O. Biton, S. Cohen, and S. Davidson. Addressing the provenance challenge using zoom. Concurr. Comput. : Pract. Exper., pages 497-506, 2008. Google ScholarDigital Library
- S. B. Davidson and J. Freire. Provenance and scientific workflows: challenges and opportunities. In SIGMOD, pages 1345-1350, 2008. Google ScholarDigital Library
- D. Deutch, A. Gilad, and Y. Moskovitch. Selective provenance for datalog programs using top-k queries. PVLDB, pages 1394-1405, 2015. Google ScholarDigital Library
- K. Elbassioni, K. Makino, and I. Rauf. On the readability of monotone boolean formulae. JoCO, pages 293-304, 2011. Google ScholarDigital Library
- M. Emms. Variants of tree similarity in a question answering task. In Proceedings of the Workshop on Linguistic Distances, pages 100-108, 2006. Google ScholarDigital Library
- E. Franconi, C. Gardent, X. I. Juarez-Castro, and L. Perez-Beltrachini. Quelo Natural Language Interface: Generating queries and answer descriptions. In Natural Language Interfaces for Web of Data, 2014.Google Scholar
- B. Glavic. Big data provenance: Challenges and implications for benchmarking. In Specifying Big Data Benchmarks - First Workshop, WBDB, pages 72-80, 2012. Google ScholarDigital Library
- T. Green, G. Karvounarakis, and V. Tannen. Provenance semirings. In PODS, pages 31-40, 2007. Google ScholarDigital Library
- E. Hemaspaandra and H. Schnoor. Minimization for generalized boolean formulas. In IJCAI, pages 566-571, 2011. Google ScholarDigital Library
- M. Herschel and M. Hlawatsch. Provenance: On and behind the screens. In SIGMOD, pages 2213-2217, 2016. Google ScholarDigital Library
- Z. G. Ives, A. Haeberlen, T. Feng, and W. Gatterbauer. Querying provenance for ranking and recommending. In TaPP, pages 9-9, 2012. Google ScholarDigital Library
- G. Karvounarakis, Z. G. Ives, and V. Tannen. Querying data provenance. In SIGMOD, pages 951-962, 2010. Google ScholarDigital Library
- F. Li and H. V. Jagadish. Constructing an interactive natural language interface for relational databases. Proc. VLDB Endow., pages 73-84, 2014. Google ScholarDigital Library
- D. Olteanu and J. Z'avodn'y. Factorised representations of query results: Size bounds and readability. In ICDT, pages 285-298, 2012. Google ScholarDigital Library
- S. Roy and D. Suciu. A formal approach to finding explanations for database queries. In SIGMOD, pages 1579-1590, 2014.2008. Google ScholarDigital Library
- Y. L. Simmhan, B. Plale, and D. Gannon. Karma2: Provenance management for data-driven workflows. Int. J. Web Service Res., pages 1-22, 2008.Google Scholar
- D. Song, F. Schilder, C. Smiley, C. Brew, T. Zielund, H. Bretz, R. Martin, C. Dale, J. Duprey, T. Miller, and J. Harrison. TR discover: A natural language interface for querying and analyzing interlinked datasets. In ISWC, pages 21-37, 2015.Google ScholarCross Ref
Index Terms
- Natural Language Explanations for Query Results
Recommendations
Provenance for natural language queries
Multiple lines of research have developed Natural Language (NL) interfaces for formulating database queries. We build upon this work, but focus on presenting a highly detailed form of the answers in NL. The answers that we present are importantly based ...
Explaining Natural Language query results
AbstractMultiple lines of research have developed Natural Language (NL) interfaces for formulating database queries. We build upon this work, but focus on presenting a highly detailed form of the answers in NL. The answers that we present are importantly ...
Comments