Abstract
An approach based on answer set programming (ASP) is proposed in this paper for representing knowledge generated from natural language text. Knowledge in the text is modeled using a Neo Davidsonian-like formalism, represented as an answer set program. Relevant common sense knowledge is additionally imported from resources such as WordNet and represented in ASP. The resulting knowledge-base can then be used to perform reasoning with the help of an ASP system. This approach can facilitate many natural language tasks such as automated question answering, text summarization, and automated question generation. ASP-based representation of techniques such as default reasoning, hierarchical knowledge organization, preferences over defaults, etc., are used to model common-sense reasoning methods required to accomplish these tasks. In this paper we describe the CASPR system that we have developed to automate the task of answering natural language questions given English text. CASPR can be regarded as a system that answers questions by “understanding” the text and has been tested on the SQuAD data set, with promising results.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Alviano, M., Faber, W., Leone, N., Perri, S., Pfeifer, G., Terracina, G.: The disjunctive datalog system DLV. In: de Moor, O., Gottlob, G., Furche, T., Sellers, A. (eds.) Datalog 2.0 2010. LNCS, vol. 6702, pp. 282–301. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-24206-9_17
Arias, J., Carro, M., Salazar, E., Marple, K., Gupta, G.: Constraint answer set programming without grounding. TPLP 18(3–4), 337–354 (2018)
Baral, C.: Knowledge Representation Reasoning and Declarative Problem Solving. Cambridge university press, New York (2003)
Baral, C., Schüller, P. (eds.): Proceedings of 1st Workshop on NLP and Automated Reasoning 2013, vol. 1044 (2013). http://ceur-ws.org/Vol-1044
Chen, D., Manning, C.: A fast and accurate dependency parser using neural networks. In: Proceedings of 2014 EMNLP, pp. 740–750 (2014)
Chen, Z., Marple, K., Salazar, E., Gupta, G., Tamil, L.: A physician advisory system for CHF based on knowledge patterns. TPLP 16(5–6), 604–618 (2016)
Davidson, D.: Inquiries into Truth and Interpretation. Oxford University Press, New York (1984)
De Marneffe, M.C., Dozat, T., et al.: Universal Stanford dependencies: a cross-linguistic typology. In: LREC, vol. 14, pp. 4585–4592 (2014)
De Marneffe, M.C., Manning, C.D.: Stanford typed dependencies manual. Technical report, Stanford University (2008)
Finkel, J.R., et al.: Incorporating non-local information into information extraction systems by Gibbs sampling. In: Proceedings of 43rd ACL, pp. 363–370 (2005)
Gebser, M., Kaminski, R., Kaufmann, B., Ostrowski, M., Schaub, T., Thiele, S.: Gringo, Clasp, Clingo, and Iclingo User Guide (2010)
Gelfond, M., Kahl, Y.: Knowledge Representation, Reasoning, and the Design of Intelligent Agents: The ASP Approach. Cambridge University Press, New York (2014)
Jonson-Laird, P.: How We Reason. Oxford University Press, New York (2009)
Kipper, K., et al.: Extending verbnet with novel verb classes. In: Proceedings of LREC 2006, Genoa, Italy, pp. 1027–1032 (2006)
Mahdisoltani, F., et al.: YAGO3: A knowledge base from multilingual Wikipedias. In: Proceedings of CIDR (2015)
Marple, K., Salazar, E., Gupta, G.: Computing stable models of normal logic programs without grounding. arXiv preprint arXiv:1709.00501 (2017)
Miller, G.A.: Wordnet: a Lexical database for English. Commun. ACM 38(11), 39–41 (1995)
Mitchell, T.M., et al.: Never-ending language learning. In: Proceedings of Twenty-Ninth AAAI Conference on Artificial Intelligence, pp. 2302–2310 (2015)
Pendharkar, D.: An ASP-based Approach to Representing and Querying Textual Knowledge. M.S. Thesis, UT Dallas. http://utdallas.edu/~gupta/dpthesis.pdf
Pendharkar, D.: CASPR. https://github.com/DhruvaPendharkar/thesis-project
Rajpurkar, P., et al.: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)
Toutanova, K., et al.: Feature-rich part-of-speech tagging with a cyclic dependency network. In: Proceedings of 2003 NAACL, pp. 173–180 (2003)
Toutanova, K., Manning, C.D.: Enriching the knowledge sources used in a maximum entropy part-of-speech tagger. In: Proceedings of EMNLP 2000, pp. 63–70 (2000)
Vo, N.H., Mitra, A., Baral, C.: The NL2KR platform for building natural language translation systems. In: Proceedings of ACL 2015, pp. 899–908 (2015)
Wikipedia contributors: Cyc – Wikipedia. Accessed 17 May 2018. https://en.wikipedia.org/w/index.php?title=Cyc&oldid=841189903
Acknowledgment
Authors thank NSF (Grant IIS 1718945) and members of their research group (Zhuo Chen, Farhad Shakerin, Elmer Salazar, Joaquin Arias, Sarat Varanasi, Kyle Marple).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Pendharkar, D., Gupta, G. (2019). An ASP Based Approach to Answering Questions for Natural Language Text. In: Alferes, J., Johansson, M. (eds) Practical Aspects of Declarative Languages. PADL 2019. Lecture Notes in Computer Science(), vol 11372. Springer, Cham. https://doi.org/10.1007/978-3-030-05998-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-05998-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-05997-2
Online ISBN: 978-3-030-05998-9
eBook Packages: Computer ScienceComputer Science (R0)