{"type":"ScholarlyArticle","title":"Cause-Effect Knowledge Acquisition and Neural Association Model for Solving A Set of Winograd Schema Problems","authors":[{"name":"Quan Liu","slug":"quan-liu","given":"Quan","family":"Liu","affiliation":"iFLYTEK Research , Hefei , China"},{"name":"Hui Jiang","slug":"hui-jiang","given":"Hui","family":"Jiang","affiliation":"‡ Dept. of EEIS , University of Science and Technology of China"},{"name":"Andrew Evdokimov","slug":"andrew-evdokimov","given":"Andrew","family":"Evdokimov","affiliation":"‡ Dept. of EEIS , University of Science and Technology of China"},{"name":"Zhen-Hua Ling","slug":"zhen-hua-ling","given":"Zhen-Hua","family":"Ling","affiliation":"iFLYTEK Research , Hefei , China"},{"name":"Xiaodan Zhu","slug":"xiaodan-zhu","given":"Xiaodan","family":"Zhu","affiliation":"‡ Dept. of EEIS , University of Science and Technology of China"},{"name":"Si Wei","slug":"si-wei","given":"Si","family":"Wei","affiliation":"§ Department of Electrical Engineering and Computer Science , York University , Canada"},{"name":"Yu Hu","slug":"yu-hu","given":"Yu","family":"Hu","affiliation":"§ Department of Electrical Engineering and Computer Science , York University , Canada"}],"abstract":"This paper focuses on the investigations in Winograd Schema (WS), a challenging problem which has been proposed for measuring progress in commonsense reasoning.Due to the lack of commonsense knowledge and training data, very little work has been found on the WS problems in recent years.Actually, there is no shortcut to solve this problem except to collect more commonsense knowledge and design suitable models.Therefore, this paper addresses a set of WS problems by proposing a knowledge acquisition method and a general neural association model.To avoid the sparseness issue, the knowledge we aim to collect is the cause-effect relationships between thousands of commonly used words.The knowledge acquisition method supports us to extract hundreds of thousands of cause-effect pairs from large text corpus automatically.Meanwhile, a neural association model (NAM) is proposed to encode the association relationships between any two discrete events.Based on the extracted knowledge and the NAM models, in this paper, we successfully build a system for solving WS problems from scratch and achieve 70.0% accuracy.Most importantly, this paper provides a flexible framework to solve WS problems based on event association and neural network methods.","doi":"10.24963/ijcai.2017/326","url":"https://ijcai.org/proceedings/2017/326","pdf":"https://ijcai.org/proceedings/2017/0326.pdf","markdown":"https://ijcai.org/proceedings/2017/326.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/326","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning A-R","track":"Main track","number":326,"pages":{"first":2344,"last":2350},"keywords":["Machine Learning: Deep Learning","Machine Learning: Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Bailey et al., 2015] Dan Bailey, Amelia Harrison, Yuliya Lierler, Vladimir Lifschitz, and Julian Michael. The wino- grad schema challenge and reasoning about correlation. In In Working Notes of the Symposium on Logical Formaliza- tions of Commonsense Reasoning, 2015.","title":"The winograd schema challenge and reasoning about correlation","authors":"Dan Bailey, Amelia Harrison, Yuliya Lierler, Vladimir Lifschitz, Julian Michael","year":"2015","venue":"Working Notes of the Symposium on Logical Formalizations of Commonsense Reasoning","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Consortium, 2007] BNC Consortium. The British Nation- al Corpus, version 3 (bnc xml edition). http://www. natcorp.ox.ac.uk, 2007.","title":"BNC Consortium. The British National Corpus, version 3","authors":null,"year":"2007","venue":null,"doi":null,"url":"http://www.natcorp.ox.ac.uk,2007","internal_url":null},{"position":3,"raw":"[Davis and Marcus, 2015] Ernest Davis and Gary Marcus. Commonsense reasoning and commonsense knowledge in artificial intelligence. Communications of the ACM, 58(9):92-103, 2015.","title":"Commonsense reasoning and commonsense knowledge in artificial intelligence","authors":"Marcus ; Davis, Ernest Davis, Gary Marcus","year":"2015","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Davis et al., 2016] Ernest Davis, Leora Morgenstern, and Charles Ortiz. The Winograd Schema Challenge. http://www.cs.nyu.edu/faculty/davise/ papers/WinogradSchemas/WS.html, 2016.","title":"The Winograd Schema Challenge","authors":"Ernest Davis, Leora Morgenstern, Charles Ortiz","year":"2016","venue":null,"doi":null,"url":"http://www.cs.nyu.edu/faculty/davise/papers/WinogradSchemas/WS.html","internal_url":null},{"position":5,"raw":"[Graff et al., 2003] David Graff, Junbo Kong, Ke Chen, and Kazuaki Maeda. English gigaword. Linguistic Data Con- sortium, Philadelphia, 2003.","title":"English gigaword. Linguistic Data Consortium","authors":"David Graff, Junbo Kong, Ke Chen, Kazuaki Maeda","year":"2003","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hill et al., 2015] Felix Hill, Antoine Bordes, Sumit Chopra, and Jason Weston. The Goldilocks Principle: Reading children's books with explicit memory representations. arXiv preprint arXiv:1511.02301, 2015.","title":"The Goldilocks Principle: Reading children's books with explicit memory representations","authors":"Felix Hill, Antoine Bordes, Sumit Chopra, Jason Weston","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hinton et al., 2012] Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, and Ruslan R Salakhut- dinov. Improving neural networks by preventing co- adaptation of feature detectors. arXiv preprint arX- iv:1207.0580, 2012.","title":"Improving neural networks by preventing coadaptation of feature detectors","authors":"Geoffrey E Hinton, Nitish Srivastava, Alex Krizhevsky, Ilya Sutskever, Ruslan R Salakhutdinov","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Kruengkrai et al., 2014] Canasai Kruengkrai, Naoya Inoue, Jun Sugiura, and Kentaro Inui. An example-based ap- proach to difficult pronoun resolution. In PACLIC, pages 358-367, 2014.","title":"An example-based approach to difficult pronoun resolution","authors":"Kruengkrai","year":"2014","venue":"PACLIC","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[LeCun et al., 2015] Yann LeCun, Yoshua Bengio, and Ge- offrey Hinton. Deep learning. Nature, 521(7553):436- 444, 2015.","title":"Deep learning","authors":"Yann Lecun, Yoshua Bengio, Geoffrey Hinton","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lenat, 1995] Douglas B Lenat. Cyc: A large-scale invest- ment in knowledge infrastructure. Communications of the ACM, 38(11):33-38, 1995.","title":"Cyc: A large-scale investment in knowledge infrastructure","authors":"Douglas B Lenat","year":"1995","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Levesque et al., 2011] Hector J Levesque, Ernest Davis, and Leora Morgenstern. The Winograd Schema Chal- lenge. In AAAI Spring Symposium: Logical Formaliza- tions of Commonsense Reasoning, 2011.","title":"The Winograd Schema Challenge","authors":"Hector J Levesque, Ernest Davis, Leora Morgenstern","year":"2011","venue":"AAAI Spring Symposium: Logical Formalizations of Commonsense Reasoning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu and Singh, 2004] Hugo Liu and Push Singh. Concept- Net: a practical commonsense reasoning toolkit. BT tech- nology journal, 22(4):211-226, 2004.","title":"Hugo Liu and Push Singh. Concept-Net: a practical commonsense reasoning toolkit","authors":"Singh Liu","year":"2004","venue":"BT technology journal","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liu et al., 2016] Quan Liu, Hui Jiang, Zhen-Hua Ling, Xi- aodan Zhu, Si Wei, and Yu Hu. Combing context and com- monsense knowledge through neural networks for solv- ing winograd schema problems. arXiv preprint arX- iv:1611.04146, 2016.","title":"Combing context and commonsense knowledge through neural networks for solving winograd schema problems","authors":"Quan Liu, Hui Jiang, Zhen-Hua Ling, Xiaodan Zhu, Si Wei, Yu Hu","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Marcus et al., 2016] Gary Marcus, Francesca Rossi, and Manuela Veloso. Beyond the turing test. AI Magazine, 37(1), 2016.","title":"Beyond the turing test","authors":"Gary Marcus, Francesca Rossi, Manuela Veloso","year":"2016","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Michalski et al., 2013] Ryszard S Michalski, Jaime G Car- bonell, and Tom M Mitchell. Machine learning: An arti- ficial intelligence approach. Springer Science & Business Media, 2013.","title":"Machine learning: An artificial intelligence approach","authors":"Jaime G Ryszard S Michalski, Tom M Carbonell, Mitchell","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Miller, 1995] George A Miller. WordNet: a lexical database for english. Communications of the ACM, 38(11):39-41, 1995.","title":"WordNet: a lexical database for english","authors":"George A Miller","year":"1995","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mnih et al., 2015] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Belle- mare, Alex Graves, Martin Riedmiller, Andreas K Fidje- land, Georg Ostrovski, et al. Human-level control through deep reinforcement learning. Nature, 518(7540):529-533, 2015.","title":"Human-level control through deep reinforcement learning","authors":"Mnih","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Morgenstern and Ortiz Jr, 2015] Leora Morgenstern and Charles L Ortiz Jr. The winograd schema challenge: Evaluating progress in commonsense reasoning. In AAAI, pages 4024-4026, 2015.","title":"The winograd schema challenge: Evaluating progress in commonsense reasoning","authors":"Ortiz Morgenstern, ; Jr, Leora Morgenstern, Charles L Ortiz","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Morgenstern et al., 2016] Leora Morgenstern, Ernest Davis, and Charles L Ortiz Jr. Planning, executing, and evaluating the Winograd Schema Challenge. AI Magazine, 37(1):50- 54, 2016.","title":"Planning, executing, and evaluating the Winograd Schema Challenge","authors":"Leora Morgenstern, Ernest Davis, Charles L Ortiz","year":"2016","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mueller, 2014] Erik T Mueller. Commonsense Reasoning: An Event Calculus Based Approach. Morgan Kaufmann, 2014.","title":"Commonsense Reasoning: An Event Calculus Based Approach","authors":"Erik T Mueller","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Nair and Hinton, 2010] Vinod Nair and Geoffrey E Hinton. Rectified linear units improve restricted boltzmann ma- chines. In Proceedings of ICML, pages 807-814, 2010.","title":"Rectified linear units improve restricted boltzmann machines","authors":"Vinod Nair, Geoffrey E Hinton","year":"2010","venue":"Proceedings of ICML","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Osgood, 1952] Charles E Osgood. The nature and measure- ment of meaning. Psychological bulletin, 49(3):197, 1952.","title":"The nature and measurement of meaning","authors":"E Charles, Osgood","year":"1952","venue":"Psychological bulletin","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Peng et al., 2015] Haoruo Peng, Daniel Khashabi, and Dan Roth. Solving hard coreference problems. Urbana, 51:61801, 2015.","title":"Solving hard coreference problems","authors":"Peng","year":"2015","venue":"Urbana","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Rahman and Ng, 2012] Altaf Rahman and Vincent Ng. Re- solving complex cases of definite pronouns: the winograd schema challenge. In Proceedings of EMNLP-CoNLL, pages 777-789, 2012.","title":"Resolving complex cases of definite pronouns: the winograd schema challenge","authors":"Ng Rahman, Altaf Rahman, Vincent Ng","year":"2012","venue":"Proceedings of EMNLP-CoNLL","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Schüller, 2014] Peter Schüller. Tackling winograd schemas by formalizing relevance theory in knowledge graphs. In Proceedings of the Fourteenth International Conference on Principles of Knowledge Representation and Reason- ing, pages 358-367. AAAI Press, 2014.","title":"Tackling winograd schemas by formalizing relevance theory in knowledge graphs","authors":"Peter Schüller","year":"2014","venue":"Proceedings of the Fourteenth International Conference on Principles of Knowledge Representation and Reasoning","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Sharma et al., 2015] Arpit Sharma, Nguyen Ha Vo, Somak Aditya, and Chitta Baral. Towards addressing the wino- grad schema challenge-building and using a semantic pars- er and a knowledge hunting module. In IJCAI, pages 1319-1325, 2015.","title":"Towards addressing the winograd schema challenge-building and using a semantic parser and a knowledge hunting module","authors":"Arpit Sharma, Ha Nguyen, Somak Vo, Chitta Aditya, Baral","year":"2015","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/190"},{"position":27,"raw":"[Sharma, 2014] Arpit Sharma. Solving winograd schema challenge: Using semantic parsing, automatic knowledge acquisition and logical reasoning. PhD thesis, Arizona State University, 2014.","title":"Solving winograd schema challenge: Using semantic parsing, automatic knowledge acquisition and logical reasoning","authors":"Arpit Sharma","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Winograd, 1972] Terry Winograd. Understanding natural language. Cognitive psychology, 3(1):1-191, 1972.","title":"Terry Winograd. Understanding natural language","authors":"Winograd","year":"1972","venue":"Cognitive psychology","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xue et al., 2014] Shaofei Xue, Ossama Abdel-Hamid, Hui Jiang, Lirong Dai, and Qingfeng Liu. Fast adaptation of deep neural network based on discriminant codes for speech recognition. Audio, Speech, and Language Pro- cessing, IEEE/ACM Trans. on, 22(12):1713-1725, 2014.","title":"Fast adaptation of deep neural network based on discriminant codes for speech recognition. Audio, Speech, and Language Processing","authors":"Xue","year":"2014","venue":"IEEE/ACM Trans. on","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhu et al., 2015] Yukun Zhu, Ryan Kiros, Rich Zemel, Rus- lan Salakhutdinov, Raquel Urtasun, Antonio Torralba, and Sanja Fidler. Aligning books and movies: Towards story- like visual explanations by watching movies and reading books. In Proceedings of ICCV, pages 19-27, 2015.","title":"Aligning books and movies: Towards storylike visual explanations by watching movies and reading books","authors":"Yukun Zhu, Ryan Kiros, Rich Zemel, Ruslan Salakhutdinov, Raquel Urtasun, Antonio Torralba, Sanja Fidler","year":"2015","venue":"Proceedings of ICCV","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}