A Marker Passing Approach to Winograd Schemas
Abstract
This paper approaches a solution of Winograd Schemas with a marker passing algorithm which operates on an automatically generated semantic graph. The semantic graph contains common sense facts from data sources form the semantic web like domain ontologies e.g. from Linked Open Data (LOD), WordNet, Wikidata, and ConceptNet. Out of those facts, a semantic decomposition algorithm selects relevant facts for the concepts used in the Winograd Schema and adds them to the semantic graph. Markers are propagated through the graph and used to identify an answer to the Winograd Schema. Depending on the encoded knowledge in the graph (connectionist view of world knowledge) and the information encoded on the marker (for symbolic reasoning) our approach selects the answers. With this selection, the marker passing approach is able to beat the state-of-the-art approach by about 12%.
Keywords
Semantic web LOD Winograd Schema Common sense reasoning Symbolic connectionist AIReferences
- 1.Arenas, M., Grau, B.C., Kharlamov, E., Marciuška, Š., Zheleznyakov, D.: Faceted search over RDF-based knowledge graphs. Web. Semant.: Sci. Serv. Agents World Wide Web 37–38, 55–74 (2016). https://doi.org/10.1016/j.websem.2015.12.002. http://www.sciencedirect.com/science/article/pii/S1570826815001432CrossRefGoogle Scholar
- 2.Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ISWC 2007, ASWC 2007. LNCS, vol. 4825, pp. 722–735. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-76298-0_52. (Chapter 52)CrossRefGoogle Scholar
- 3.Austin, J.: Distributed associative memories for high-speed symbolic reasoning. Fuzzy Sets Syst. 82(2), 223–233 (1996). https://doi.org/10.1016/0165-0114(95)00258-8. http://eprints.whiterose.ac.uk/1871/1/austinj18.pdfCrossRefGoogle Scholar
- 4.Collins, A., Quillian, R.: Retrieval time from semantic memory. J. Verbal Learn. Verbal Behav. 8(2), 240–247 (1968). https://doi.org/10.1016/S0022-5371(69)80069-1. http://linkinghub.elsevier.com/retrieve/pii/S0022537169800691CrossRefGoogle Scholar
- 5.Crestani, F.: Application of spreading activation techniques in information retrieval. Artif. Intell. Rev. 11(6), 453–482 (1997). https://doi.org/10.1023/A:1006569829653CrossRefGoogle Scholar
- 6.Davis, E., Morgenstern, L., Ortiz, C.: The first Winograd schema challenge at IJCAI-16. AI Mag. 38(3), 97–98 (2017). https://doi.org/10.1609/aimag.v38i4.2734. https://dblp.org/rec/journals/aim/DavisMO17CrossRefGoogle Scholar
- 7.Ecke, A., Peñaloza, R., Turhan, A.Y.: Similarity-based relaxed instance queries. J. Appl. Logic 13(1), 480–508 (2015). https://doi.org/10.1016/j.jal.2015.01.002. http://www.sciencedirect.com/science/article/pii/S1570868315000038Workshop on Weighted Logics for AI - 2013MathSciNetCrossRefzbMATHGoogle Scholar
- 8.Emami, A., Trischler, A., Suleman, K., Cheung, J.C.K.: A generalized knowledge hunting framework for the Winograd schema challenge. In: NAACL-HLT (2018). https://dblp.org/rec/conf/naacl/EmamiTSC18
- 9.Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639), 115–118 (2017). https://doi.org/10.1038/nature21056. http://www.nature.com/doifinder/10.1038/nature21056CrossRefGoogle Scholar
- 10.Fähndrich, J., Weber, S., Ahrndt, S.: Design and use of a semantic similarity measure for interoperability among agents. In: Klusch, M., Unland, R., Shehory, O., Pokahr, A., Ahrndt, S. (eds.) Multiagent System Technologies, vol. 9872, pp. 41–57. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-45889-2_4CrossRefGoogle Scholar
- 11.Furbach, U., Schon, C.: Commonsense reasoning meets theorem proving. In: Klusch, M., Unland, R., Shehory, O., Pokahr, A., Ahrndt, S. (eds.) Multiagent System Technologies. LNCS, vol. 9872, pp. 3–17. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-45889-2_1CrossRefGoogle Scholar
- 12.Ghallab, M., Nau, D., Traverso, P.: The actor’s view of automated planning and acting: a position paper. Artif. Intell. 208, 1–17 (2014). https://doi.org/10.1016/j.artint.2013.11.002. http://linkinghub.elsevier.com/retrieve/pii/S0004370213001173CrossRefGoogle Scholar
- 13.Jones, M.N., Willits, J., Dennis, S.: Models of Semantic Memory, Models of Semantic Memory, vol. 1. Oxford University Press, Oxford (2015). https://doi.org/10.1093/oxfordhb/9780199957996.013.11CrossRefGoogle Scholar
- 14.Kurzweil, R.: The Singularity is Near. Gerald Duckworth & Co, London (2005)Google Scholar
- 15.Lecue, F.: Applying machine reasoning and learning in real world applications. In: Pan, J.Z., et al. (eds.) Reasoning Web 2016. LNCS, vol. 9885, pp. 241–257. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-49493-7_7CrossRefGoogle Scholar
- 16.Levesque, H., Davis, E., Morgenstern, L.: The Winograd schema challenge. In: Proceedings of the Thirteenth International Conference on Principles of Knowledge Representation and Reasoning, vol. 46, pp. 552–561 (2011)Google Scholar
- 17.Liu, Q., Jiang, H., Ling, Z.H., Zhu, X., Wei, S., Hu, Y.: Combing context and commonsense knowledge through neural networks for solving Winograd schema problems. Assoc. Adv. Artif. Intell. (2017). http://dblp.org/rec/journals/corr/LiuJLZWH16
- 18.Manning, C., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S., McClosky, D.: The stanford CoreNLP natural language processing toolkit. In: ACL (2014). http://dblp.org/rec/conf/acl/ManningSBFBM14
- 19.Morgenstern, L., Davis, E., Ortiz Jr, C.: Planning, executing, and evaluating the Winograd schema challenge. AI Mag. (2016). https://dblp.org/rec/journals/aim/MorgensternDO16
- 20.Neely, J.H.: Semantic priming and retrieval from lexical memory: roles of inhibitionless spreading activation and limited-capacity attention. J. Exp. Psychol.: Gen. 106(3), 226–254 (1977)CrossRefGoogle Scholar
- 21.Pace-Sigge, M.: Spreading Activation Lexical Priming and the Semantic Web. Early Psycholinguistic Theories, Corpus Linguistics and AI Applications. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-90719-2CrossRefGoogle Scholar
- 22.Peng, H., Khashabi, D., Roth, D.: Solving hard coreference problems. In: Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2015). http://dblp.org/rec/conf/naacl/PengKR15
- 23.Rahman, A., Ng, V.: Resolving complex cases of definite pronouns: the Winograd schema challenge. In: Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 777–789 (2012)Google Scholar
- 24.Richard-Bollans, A., Álvarez, L.G., Cohn, A.G.: The role of pragmatics in solving the Winograd schema challenge. In: COMMONSENSE (2017). https://dblp.org/rec/conf/commonsense/Richard-Bollans17
- 25.Searle, J.: Minds, brains, and programs. Behav. Brain Sci. 3(3), 417–424 (1980). https://doi.org/10.1017/S0140525X00005756. http://www.journals.cambridge.org/abstract_S0140525X00005756CrossRefGoogle Scholar
- 26.Sharma, A., Vo, N.H., Aditya, S., Baral, C.: Towards addressing the Winograd schema challenge-building and using a semantic parser and a knowledge hunting module. In: International Joint Conference on Artificial Intelligence, pp. 1319–1325 (2015)Google Scholar
- 27.Shastri, L., Ajjanagadde, V.: From simple associations to systematic reasoning: a connectionist representation of rules, variables and dynamic bindings using temporal synchrony. Behav. Brain Sci. 16(03), 417–451 (2010). https://doi.org/10.1017/S0140525X00030910. http://www.journals.cambridge.org/abstract_S0140525X00030910CrossRefGoogle Scholar
- 28.Smith, E., Shoben, E., Rips, L.: Structure and process in semantic memory: a featural model for semantic decisions. Psychol. Rev. 81(3), 214–241 (1974). https://doi.org/10.1037/h0036351CrossRefGoogle Scholar
- 29.Sun, R.: A connectionist model for commonsense reasoning incorporating rules and similarities. Knowl. Acquis. 4(3), 293–321 (1992). https://doi.org/10.1016/1042-8143(92)90020-2CrossRefGoogle Scholar
- 30.Wang, F.Y., et al.: Where does AlphaGo go: from church-turing thesis to AlphaGo thesis and beyond. IEEE/CAA J. Autom. Sin. 3(2), 113–120 (2016). https://doi.org/10.1109/JAS.2016.7471613CrossRefGoogle Scholar
- 31.de Winter, J., Dodou, D.: Why the Fitts list has persisted throughout the history of function allocation. Cognit. Technol. Work. 16, 1–11 (2014). https://doi.org/10.1007/s10111-011-0188-1. http://dx.doi.org/10.1007/s10111-011-0188-1CrossRefGoogle Scholar
- 32.Yamaguchi, A., Kozaki, K., Yamamoto, Y., Masuya, H., Kobayashi, N.: Semantic graph analysis for federated LOD surfing in life sciences. JIST 10675(5), 268–276 (2017). https://doi.org/10.1007/978-3-319-70682-5-18CrossRefGoogle Scholar
- 33.Yampolskiy, R.: AI-complete, AI-hard, or AI-easy - classification of problems in AI. In: Twenty-third Midwest Artificial Intelligence and Cognitive Science Conference, pp. 94–101 (2012). http://ceur-ws.org/Vol-841/submission_3.pdf