Learning OWL 2 Property Characteristics as an Explanation for an RNN

• Autorzy: Potoniec J.

Identyfikatory

DOI

10.24425/bpasts.2020.134625

• Języki publikacji: EN

Abstrakty

EN

We propose an approach to indirectly learn the Web Ontology Language OWL 2 property characteristics as an explanation for a deep recurrent neural network (RNN). The input is a knowledge graph represented in Resource Description Framework (RDF) and the output are scored axioms representing the characteristics. The proposed method is capable of learning all the characteristics included in OWL 2: functional, inverse functional, reflexive and irreflexive, symmetric and asymmetric, transitive. We report and discuss experimental evaluation on DBpedia 2016-10, showing that the proposed approach has advantages over a simple counting baseline.

Słowa kluczowe

EN

recurrent neural network; ontology learning; property characteristics; knowledge graphs; semantic web; deep learning

PL

rekurencyjne sieci neuronowe; nauka ontologii; charakterystyka właściwości; wykresy wiedzy; sieć semantyczna; głęboka nauka

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2020
• Tom: Vol. 68, nr 6
• Strony: 1481--1490
• Opis fizyczny: Bibliogr. 43 poz., rys., tab.

Twórcy

autor

Potoniec J.

• Institute of Computing, Poznan University of Technology, ul. Piotrowo 2, 60-965 Poznan, Poland
• Center for Artificial Intelligence and Machine Learning, Poznan University of Technology, ul. Piotrowo 2, 60-965 Poznan, Poland

Bibliografia

• [1] D. Choiński and M. Senik, “Distributed control systems integration and management with an ontology-based multi-agent system”, Bull. Pol. Ac.: Tech. 66 (5), 613–620 (2018).
• [2] P. Różewski and O. Zaikin, “Integrated mathematical model of competence-based learning-teaching process”, Bull. Pol. Ac.: Tech. 63 (1), 245–259 (2015).
• [3] O. Zaikin, R. Tadeusiewicz, P. Różewski, L.B. Kofoed, M. Malinowska, and A. Żyławski, “Teachers’ and students’ motivation model as a strategy for open distance learning processes”, Bull. Pol. Ac.: Tech. 64 (4), 943–955 (2016).
• [4] S. Ambroszkiewicz, W. Bartyna, M. Faderewski, and G. Terlikowski, “Multirobot system architecture: environment representation and protocols”, Bull. Pol. Ac.: Tech. 58 (1), 3–13 (2010).
• [5] M. Schneider, “OWL 2 web ontology language RDF-based semantics (second edition)”, W3C, W3C Recommendation, 2012.
• [6] K. Krawiec, R. Slowinski, and I. Szczesniak, “Pedagogical method for extraction of symbolic knowledge from neural networks”, in Rough Sets and Current Trends in Computing, First International Conference, ser. Lecture Notes in Computer Science, vol. 1424, Springer, 1998, pp. 436–443. doi: 10.1007/3-540-69115-4_60.
• [7] D. Wood, M. Lanthaler, and R. Cyganiak, “RDF 1.1 concepts and abstract syntax”, W3C, W3C Recommendation, 2014. http://www.w3.org/ TR/ 2014/ REC- rdf11-concepts-20140225/.
• [8] G. Carothers and E. Prud’hommeaux, “RDF 1.1 turtle”, W3C, W3C Recommendation, 2014. http://www.w3.org/TR/2014/REC- turtle-20140225/.
• [9] J. Lehmann, R. Isele, M. Jakob, A. Jentzsch, D. Kontokostas, P.N. Mendes, S. Hellmann, M. Morsey, P. van Kleef, S. Auer, and C. Bizer, “Dbpedia – A large-scale, multilingual knowledge base extracted from wikipedia”, Semantic Web 6 (2), 167–195 (2015). doi: 10.3233/SW-140134.
• [10] M. Horridge and P. Patel-Schneider, “OWL 2 web ontology language manchester syntax (second edition)”, W3C, W3C Note, 2012. http://www.w3.org/TR/2012/NOTE- owl2- manchester-syntax-20121211/.
• [11] J. Potoniec, P. Jakubowski, and A. Lawrynowicz, “Swift linked data miner: Mining OWL 2 EL class expressions directly from online RDF datasets”, J. Web Semant. 46-47, 31–50 (2017). doi: 10.1016/j.websem.2017.08.001.
• [12] J. Völker, D. Fleischhacker, and H. Stuckenschmidt, “Automatic acquisition of class disjointness”, J. Web Semant. 35, 124–139 (2015). doi: 10.1016/j.websem.2015.07.001.
• [13] A. Lawrynowicz and J. Potoniec, “Pattern based feature construction in semantic data mining”, Int. J. Semantic Web Inf. Syst. 10 (1), 27–65 (2014).
• [14] J. Potoniec and A. Lawrynowicz, “Combining ontology class expression generation with mathematical modeling for ontology learning”, in Proc. of the Twenty-Ninth AAAI Conference on Artificial Intelligence, AAAI Press, 2015, pp. 4198–4199 [Online] Available: http://www.aaai.org/ ocs/ index.php/ AAAI/AAAI15/ paper/view/9526.
• [15] J. Lehmann, S. Auer, L. Bühmann, and S. Tramp, “Class expression learning for ontology engineering”, J. Web Semant. 9 (1), 71–81 (2011). doi: 10.1016/j.websem.2011.01.001.
• [16] D. Fleischhacker, J. Völker, and H. Stuckenschmidt, “Mining RDF data for property axioms”, in On the Move to Meaningful Internet Systems: OTM 2012, Confederated International Conferences: CoopIS, DOA-SVI, and ODBASE 2012, ser. Lecture Notes in Computer Science 7566. Springer, 2012, pp. 718–735. doi: 10.1007/978-3-642-33615-7_18.
• [17] G. Rizzo, C. d’Amato, N. Fanizzi, and F. Esposito, “Tree-based models for inductive classification on the web of data”, J. Web Semant. 45, 1–22 (2017). doi: 10.1016/j.websem.2017.05.001.
• [18] L. Galárraga, C. Teflioudi, K. Hose, and F.M. Suchanek, “Fast rule mining in ontological knowledge bases with AMIE+”, VLDB J. 24 (6), 707–730 (2015).
• [19] J. Lehmann and J. Völker, Perspectives on Ontology Learning, ser. Studies on the Semantic Web. vol. 18. IOS Press, 2014.
• [20] F. Horn and K.-R. Müller, “Predicting pairwise relations with neural similarity encoders”, Bull. Pol. Ac.: Tech. 66 (6), 821–830 (2018).
• [21] P. Ristoski and H. Paulheim, “Rdf2vec: RDF graph embeddings for data mining”, in The Semantic Web – ISWC 2016 – 15th International Semantic Web Conference, ser. Lecture Notes in Computer Science, vol. 9981, 2016, pp. 498–514. doi: 10.1007/978-3-319-46523-4_30.
• [22] B. Shi and T. Weninger, “Proje: Embedding projection for knowledge graph completion”, in Proc. of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI Press, 2017, pp. 1236–1242. [Online]. Available: http://aaai.org/ ocs/ index.php/AAAI/ AAAI17/ paper/view/14279.
• [23] A. Bordes, N. Usunier, A. García-Durán, J. Weston, and O. Yakhnenko, “Translating embeddings for modeling multirelational data”, in Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013, 2013, pp. 2787–2795. [Online]. Available: http://papers.nips.cc/paper/ 5071-translating-embeddings-for-modeling-multi-relational-data.
• [24] G. Petrucci, M. Rospocher, and C. Ghidini, “Expressive ontology learning as neural machine translation”, J. Web Semant. 52-53, 66–82 (2018). doi: 10.1016/j.websem.2018.10.002.
• [25] W. Song, Z. Duan, Z. Yang, H. Zhu, M. Zhang, and J. Tang, “Explainable knowledge graph-based recommendation via deep reinforcement learning”, CoRR, vol. abs/1906.09506, 2019.
• [26] P.G. Omran, K. Wang, and Z. Wang, “Scalable rule learning via learning representation”, in Proc. of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, pp. 2149–2155, ijcai.org, 2018.
• [27] B. Yang, W. Yih, X. He, J. Gao, and L. Deng, “Embedding entities and relations for learning and inference in knowledge bases”, in 3rd International Conference on Learning Representations, ICLR 2015, 2015.
• [28] K. Cho, B. van Merrienboer, Ç. Gülçehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio, “Learning phrase representations using RNN encoder-decoder for statistical machine translation”, in Proc. of the 2014 Conference on Empirical Methods in Natural Language Processing, EMNLP 2014, ACL, 2014, pp. 1724–1734.
• [29] Y. Gal and Z. Ghahramani, “A theoretically grounded application of dropout in recurrent neural networks”, in Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain, 2016, pp. 1019–1027.
• [30] J. Chung, Ç. Gülçehre, K. Cho, and Y. Bengio, “Empirical evaluation of gated recurrent neural networks on sequence modeling”, CoRR, vol. abs/1412.3555, 2014.
• [31] Wikipedia contributors, “Template: infobox person – Wikipedia, the free encyclopedia”, https://en.wikipedia.org/w/index.php?title=Template:Infobox_person&oldid=947719598, 2020 [On-line; accessed 6-May-2020].
• [32] Wikipedia contributors, “Sister city – Wikipedia, the free encyclopedia”, https://en.wikipedia.org/w/index.php?title=Sister_city&oldid=952706943, 2020 [Online; accessed 6-May-2020].
• [33] N. Clarke, “Globalising care? town twinning in britain since 1945”, Geoforum 42 (1), 115–125, 2011.
• [34] Wikipedia contributors, “Template: infobox automobile – Wikipedia, the free encyclopedia”, https://en.wikipedia.org/w/index.php?title=Template:Infobox_automobile&oldid=948513824, 2020 [Online; accessed 6-May-2020].
• [35] Wikipedia contributors, “Sister paper – Wikipedia, the free encyclopedia”, https://en.wikipedia.org/w/index.php?title=Sister_paper&oldid=918056329, 2019 [Online; accessed 6-May-2020].
• [36] Wikipedia contributors, “Sister station – Wikipedia, the free encyclopedia”, https://en.wikipedia.org/ w/ index.php? title= Sister_station&oldid=944023428, 2020 [Online; accessed 6-May-2020].
• [37] Wikipedia contributors, “Template: infobox office holder – Wikipedia, the free encyclopedia”, https://en.wikipedia.org/w/index.php?title=Template:Infobox_officeholder&oldid=893739564, 2020 [Online; accessed 6-May-2020].
• [38] Wikipedia contributors, “Template: infobox canal: Difference between revisions – Wikipedia, the free encyclopedia”, https://en.wikipedia.org/w/index.php?title=Template%3AInfobox_canal&type=revision&diff=951115764&oldid=751761235,2020 [Online; accessed 6-May-2020].
• [39] W.R. Thompson, “Identifying rivals and rivalries in world politics”, International Studies Quarterly 45 (4), 557–586 (2001). doi: 10.1111/0020-8833.00214.
• [40] C.M. Keet and A. Artale, “Representing and reasoning over a taxonomy of part-whole relations”, Applied Ontology 3 (1-2), 91–110 (2008). doi: 10.3233/AO-2008-0049.
• [41] C. Masolo, S. Borgo, A. Gangemi, N. Guarino, and A. Oltramari, “Wonderweb deliverable D18: Ontology library (final)”, Tech. Rep., IST Project 2001-33052 WonderWeb, 2003. http://www.loa.istc.cnr.it/old/Papers/D18.pdf.
• [42] D.M. Eberhard, G.F. Simons, and C.D. Fennig, Eds., Ethnologue: Languages of the World. Twenty-third edition. Dallas, Texas: SIL International., 2020. Online version: http://www.ethnologue.com.
• [43] W. Ride, H. Cogger, C. Dupuis, O. Kraus, A. Minelli, F.C. Thompson, and P. Tubbs, Eds., International code of zoological nomenclature Fourth Edition. The International Trust for Zoological Nomenclature, 1999.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).