End-to-End Representation Learning for Question Answering with Weak Supervision

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 769)

Abstract

In this paper we present a knowledge base question answering system for participation in Task 4 of the QALD-7 shared task. Our system is an end-to-end neural architecture for constructing a structural semantic representation of a natural language question. We define semantic representations as graphs that are generated step-wise and can be translated into knowledge base queries to retrieve answers. We use a convolutional neural network (CNN) model to learn vector encodings for the questions and the semantic graphs and use it to select the best matching graph for the input question. We show on two different datasets that our system is able to successfully generalize to new data.

Keywords

Semantic web Question-answering Representation learning Convolutional neural networks Semantic parsing Weak supervision 

References

  1. 1.
    Aghaebrahimian, A., Jurčíček, F.: Open-domain factoid question answering via knowledge graph search. In: Proceedings of 2016 NAACL Human-Computer Question Answering Workshop, pp. 22–28 (2016)Google Scholar
  2. 2.
    Bao, J., Duan, N., Yan, Z., Zhou, M., Zhao, T.: Constraint-based question answering with knowledge graph. In: Proceedings of the 26th International Conference on Computational Linguistics (COLING), pp. 2503–2514 (2016)Google Scholar
  3. 3.
    Berant, J., Chou, A., Frostig, R., Liang, P.: Semantic parsing on freebase from question-answer Pairs. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1533–1544 (2013)Google Scholar
  4. 4.
    Berant, J., Liang, P.: Semantic parsing via paraphrasing. In: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics, pp. 1415–1425 (2014)Google Scholar
  5. 5.
    Bordes, A., Usunier, N., Chopra, S., Weston, J.: Large-scale Simple Question Answering with Memory Networks. arXiv preprint (2015)Google Scholar
  6. 6.
    Diefenbach, D., Singh, K., Maret, P.: WDAqua-core0: a question answering component for the research community. In: Proceedings of the 7th Open Challenge on Question Answering over Linked Data (QALD-7) at ESWC (2017)Google Scholar
  7. 7.
    Dong, L., Lapata, M.: Language to logical form with neural attention. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, pp. 33–43 (2016)Google Scholar
  8. 8.
    Dong, L., Wei, F., Zhou, M., Xu, K.: Question answering over freebase with multi-column convolutional neural networks. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pp. 260–269 (2015)Google Scholar
  9. 9.
    Hakimov, S., Unger, C., Walter, S., Cimiano, P.: Applying semantic parsing to question answering over linked data: addressing the lexical gap. In: Biemann, C., Handschuh, S., Freitas, A., Meziane, F., Métais, E. (eds.) NLDB 2015. LNCS, vol. 9103, pp. 103–109. Springer, Cham (2015). doi:10.1007/978-3-319-19581-0_8 CrossRefGoogle Scholar
  10. 10.
    Huang, P., He, X., Gao, J., Deng, L., Acero, A., Heck, L.: Learning deep structured semantic models for web search using clickthrough data. In: The 22nd ACM International Conference on Information & Knowledge Management (CIKM), pp. 2333–2338 (2013)Google Scholar
  11. 11.
    Jain, S.: Question answering over knowledge base using factual memory networks. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 109–115 (2016)Google Scholar
  12. 12.
    Kingma, D., Ba, J.: Adam: A Method for Stochastic Optimization. arXiv preprint (2014)Google Scholar
  13. 13.
    Lukovnikov, D., Fischer, A., Lehmann, J., Auer, S.: Neural network-based question answering over knowledge graphs on word and character level. In: Proceedings of the 26th International Conference on World Wide Web - WWW 2017, pp. 1211–1220 (2017)Google Scholar
  14. 14.
    Manning, C.D., Bauer, J., Finkel, J., Bethard, S.J., Surdeanu, M., McClosky, D.: The stanford CoreNLP natural language processing toolkit. In: Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics, pp. 55–60 (2014)Google Scholar
  15. 15.
    Reddy, S., Lapata, M., Steedman, M.: Large-scale semantic parsing without question-answer Pairs. Trans. Assoc. Comput. Linguist. 2, 377–392 (2014)Google Scholar
  16. 16.
    Reddy, S., Täckström, O., Collins, M., Kwiatkowski, T., Das, D., Steedman, M., Lapata, M.: Transforming dependency structures to logical forms for semantic parsing. Trans. Assoc. Comput. Linguist. 4, 127–140 (2016)Google Scholar
  17. 17.
    Unger, C., Forascu, C., Lopez, V., Ngomo, A.-C.N., Cabrio, E., Cimiano, P., Walter, S.: Question answering over linked data (QALD-5). In: CEUR Workshop Proceedings, vol. 1391 (2015)Google Scholar
  18. 18.
    Van Der Maaten, L., Hinton, G.: Visualizing high-dimensional data using t-sne. J. Mach. Learn. Res. 9, 2579–2605 (2008)MATHGoogle Scholar
  19. 19.
    Vrandečić, D., Krötzsch, M.: Wikidata: a free collaborative knowledgebase. Commun. ACM 57(10), 78–85 (2014)CrossRefGoogle Scholar
  20. 20.
    Yao, X.: Lean question answering over freebase from scratch. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 66–70 (2015)Google Scholar
  21. 21.
    Yao, X., Van Durme, B.: Information extraction over structured data: question answering with freebase. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pp. 956–966 (2014)Google Scholar
  22. 22.
    Yih, W.T., Chang, M., He, X., Gao, J.: Semantic parsing via staged query graph generation: question answering with knowledge base. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, pp. 1321–1331 (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer ScienceTechnische Universität DarmstadtDarmstadtGermany

Personalised recommendations