{"type":"ScholarlyArticle","title":"Neural Program Induction for KBQA Without Gold Programs or Query Annotations","authors":[{"name":"Ghulam Ahmed Ansari","slug":"ghulam-ahmed-ansari","given":"Ghulam Ahmed","family":"Ansari","affiliation":"IBM Research , India"},{"name":"Amrita Saha","slug":"amrita-saha","given":"Amrita","family":"Saha","affiliation":"IBM Research , India"},{"name":"Vishwajeet Kumar","slug":"vishwajeet-kumar","given":"Vishwajeet","family":"Kumar","affiliation":"Indian Institute of Technology Bombay , India"},{"name":"Mohan Bhambhani","slug":"mohan-bhambhani","given":"Mohan","family":"Bhambhani","affiliation":"IBM Research , India"},{"name":"Karthik Sankaranarayanan","slug":"karthik-sankaranarayanan","given":"Karthik","family":"Sankaranarayanan","affiliation":"IBM Research , India"},{"name":"Soumen Chakrabarti","slug":"soumen-chakrabarti","given":"Soumen","family":"Chakrabarti","affiliation":"Indian Institute of Technology Bombay , India"}],"abstract":"Neural Program Induction (NPI) is a paradigm for decomposing high-level tasks such as complex question-answering over knowledge bases (KBQA) into executable programs by employing neural models. Typically, this involves two key phases: i) inferring input program variables from the high-level task description, and ii) generating the correct program sequence involving these variables. Here we focus on NPI for Complex KBQA with only the final answer as supervision, and not gold programs. This raises major challenges; namely, i) noisy query annotation in the absence of any supervision can lead to catastrophic forgetting while learning, ii) reward becomes extremely sparse owing to the noise. To deal with these, we propose a noise-resilient NPI model, Stable Sparse Reward based Programmer (SSRP) that evades noise-induced instability through continual retrospection and its comparison with current learning behavior. On complex KBQA datasets, SSRP performs at par with hand-crafted rule-based models when provided with gold program input, and in the noisy settings outperforms state-of-the-art models by a significant margin even with a noisier query annotator.","doi":"10.24963/ijcai.2019/679","url":"https://ijcai.org/proceedings/2019/679","pdf":"https://ijcai.org/proceedings/2019/0679.pdf","markdown":"https://ijcai.org/proceedings/2019/679.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/679","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":679,"pages":{"first":4890,"last":4896},"keywords":["Machine Learning: Deep Learning","Natural Language Processing: Question Answering","Machine Learning Applications: Applications of Reinforcement Learning"],"videos":[],"references":[{"position":1,"raw":"[Bosnjak et al., 2017] Matko Bosnjak, Tim Rocktäschel, Ja- son Naradowsky, and Sebastian Riedel. Programming with a differentiable forth interpreter. In ICML 2017, Sydney, NSW, Australia, 6-11 August 2017, pages 547-556, 2017.","title":"Programming with a differentiable forth interpreter","authors":"Matko Bosnjak, Tim Rocktäschel, Jason Naradowsky, Sebastian Riedel","year":"2017","venue":"ICML 2017","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bunel et al., 2018] Rudy Bunel, Matthew J. Hausknecht, Ja- cob Devlin, Rishabh Singh, and Pushmeet Kohli. Lever- aging grammar and reinforcement learning for neural pro- gram synthesis. CoRR, abs/1805.04276, 2018.","title":"Leveraging grammar and reinforcement learning for neural program synthesis","authors":"Rudy Bunel, Matthew J Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dubey et al., 2018] Mohnish Dubey, Debayan Banerjee, Debanjan Chaudhuri, and Jens Lehmann. EARL: joint entity and relation linking for question answering over knowledge graphs. CoRR, abs/1801.03825, 2018.","title":"EARL: joint entity and relation linking for question answering over knowledge graphs","authors":"Mohnish Dubey, Debayan Banerjee, Debanjan Chaudhuri, Jens Lehmann","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[He et al., 2018] Xuanli He, Gholamreza Haffari, and Mo- hammad Norouzi. Sequence to sequence mixture model for diverse machine translation. In Proceedings of the 22nd Conference on Computational Natural Language Learn- ing, CoNLL 2018, Brussels, Belgium, October 31 -Novem- ber 1, 2018, pages 583-592, 2018.","title":"Xuanli He, Gholamreza Haffari, and Mohammad Norouzi. Sequence to sequence mixture model for diverse machine translation","authors":"He","year":"2018","venue":"Proceedings of the 22nd Conference on Computational Natural Language Learning, CoNLL 2018","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Iyyer et al., 2017] Mohit Iyyer, Wen-tau Yih, and Ming-Wei Chang. Search-based neural structured learning for se- quential question answering. In ACL, volume 1, 2017.","title":"Search-based neural structured learning for sequential question answering","authors":"Mohit Iyyer, Wen-Tau Yih, Ming-Wei Chang","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Konda and Tsitsiklis, 2003] Vijay R. Konda and John N. Tsitsiklis. On actor-critic algorithms. SIAM J. Control Optim., 42(4):1143-1166, April 2003.","title":"On actor-critic algorithms","authors":"Vijay R Konda, John N Tsitsiklis","year":"2003","venue":"SIAM J. Control Optim","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Liang et al., 2017] Chen Liang, Jonathan Berant, Quoc Le, Kenneth D. Forbus, and Ni Lao. Neural symbolic ma- chines: Learning semantic parsers on freebase with weak supervision. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, July 30 -August 4, Volume 1: Long Papers, pages 23-33, 2017.","title":"Neural symbolic machines: Learning semantic parsers on freebase with weak supervision","authors":"Chen Liang, Jonathan Berant, Quoc Le, Kenneth D Forbus, Ni Lao","year":"2017","venue":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Neelakantan et al., 2016] Arvind Neelakantan, Quoc V Le, Martin Abadi, Andrew McCallum, and Dario Amodei. Learning a natural language interface with neural pro- grammer. arXiv preprint arXiv:1611.08945, 2016.","title":"Learning a natural language interface with neural programmer","authors":"Arvind Neelakantan, V Quoc, Martin Le, Andrew Abadi, Dario Mccallum, Amodei","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Radhakrishnan et al., 2018] Priya Radhakrishnan, Partha Talukdar, and Vasudeva Varma. Elden: Improved en- tity linking using densified knowledge graphs. In Pro- ceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), volume 1, pages 1844-1853, 2018.","title":"Elden: Improved entity linking using densified knowledge graphs","authors":"Partha Priya Radhakrishnan, Vasudeva Talukdar, Varma","year":"2018","venue":"Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Reed and De Freitas, 2015] Scott Reed and Nando De Fre- itas. Neural programmer-interpreters. arXiv preprint arXiv:1511.06279, 2015.","title":"Scott Reed and Nando De Freitas","authors":"Reed, De Freitas","year":"2015","venue":"Neural programmer-interpreters","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Saha et al., 2018] Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, and Sarath Chandar. Complex sequential question answering: Towards learn- ing to converse over linked question answer pairs with a knowledge graph. In AAAI, 2018.","title":"Complex sequential question answering: Towards learning to converse over linked question answer pairs with a knowledge graph","authors":"Amrita Saha, Vardaan Pahuja, M Mitesh, Karthik Khapra, Sarath Sankaranarayanan, Chandar","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Sorokin and Gurevych, 2017] Daniil Sorokin and Iryna Gurevych. Context-aware representations for knowledge base relation extraction. In Proceedings of EMNLP, 2017.","title":"Context-aware representations for knowledge base relation extraction","authors":"Daniil Sorokin, Iryna Gurevych","year":"2017","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Titov and Le, 2018] Ivan Titov and Phong Le. Improving entity linking by modeling latent relations between men- tions. In Proceedings of the 56th Annual Meeting of the As- sociation for Computational Linguistics, ACL 2018, Mel- bourne, Australia, July 15-20, 2018, Volume 1: Long Pa- pers, 2018.","title":"Improving entity linking by modeling latent relations between mentions","authors":"Le ; Titov, Ivan Titov, Phong Le","year":"2018","venue":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Wang et al., 2018] William Yang Wang, Weiran Xu, and Pengda Qin. Robust distant supervision relation extrac- tion via deep reinforcement learning. In Proceedings of the 56th Annual Meeting of the Association for Computa- tional Linguistics, ACL 2018, Melbourne, Australia, July 15-20, 2018, Volume 1: Long Papers, pages 2137-2147, 2018.","title":"Robust distant supervision relation extraction via deep reinforcement learning","authors":"William Yang, Wang, Weiran Xu, Pengda Qin","year":"2018","venue":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Williams, 1992] Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforce- ment learning. In Reinforcement Learning, pages 5-32. Springer, 1992.","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","authors":"Williams Ronald","year":"1992","venue":"Reinforcement Learning","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wu et al., 2018] Zeqiu Wu, Xiang Ren, Frank F. Xu, Ji Li, and Jiawei Han. Indirect supervision for relation extrac- tion using question-answer pairs. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, WSDM 2018, Marina Del Rey, CA, USA, February 5-9, 2018, pages 646-654, 2018.","title":"Indirect supervision for relation extraction using question-answer pairs","authors":"Zeqiu Wu, Xiang Ren, Frank F Xu, Ji Li, Jiawei Han","year":"2018","venue":"Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, WSDM 2018","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Xu et al., 2016] Kun Xu, Siva Reddy, Yansong Feng, Song- fang Huang, and Dongyan Zhao. Question answering on freebase via relation extraction and textual evidence. In Proceedings of the 54th Annual Meeting of the Associa- tion for Computational Linguistics, ACL 2016, August 7- 12, 2016, Berlin, Germany, Volume 1: Long Papers, 2016.","title":"Question answering on freebase via relation extraction and textual evidence","authors":"Kun Xu, Siva Reddy, Yansong Feng, Songfang Huang, Dongyan Zhao","year":"2016","venue":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Yih et al., 2015] Wen-tau Yih, Ming-Wei Chang, Xiaodong He, and Jianfeng Gao. Semantic parsing via staged query graph generation: Question answering with knowledge base. In Proceedings of the 53rd Annual Meeting of the As- sociation for Computational Linguistics and the 7th Inter- national Joint Conference on Natural Language Process- ing of the Asian Federation of Natural Language Process- ing, ACL 2015, July 26-31, 2015, Beijing, China, Volume 1: Long Papers, pages 1321-1331, 2015.","title":"Semantic parsing via staged query graph generation: Question answering with knowledge base","authors":"Wen-Tau Yih, Ming-Wei Chang, Xiaodong He, Jianfeng Gao","year":"2015","venue":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL 2015","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yih et al., 2016] Wen-tau Yih, Matthew Richardson, Chris Meek, Ming-Wei Chang, and Jina Suh. The value of se- mantic parse labeling for knowledge base question answer- ing. In Proceedings of the 54th Annual Meeting of the As- sociation for Computational Linguistics (Volume 2: Short Papers), volume 2, pages 201-206, 2016.","title":"The value of semantic parse labeling for knowledge base question answering","authors":"Wen-Tau Yih, Matthew Richardson, Chris Meek, Ming-Wei Chang, Jina Suh","year":"2016","venue":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Yu et al., 2017] Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cícero Nogueira dos Santos, Bing Xiang, and Bowen Zhou. Improved neural relation detection for knowledge base question answering. In Proceedings of the 55th An- nual Meeting of the Association for Computational Lin- guistics, ACL 2017, Vancouver, Canada, July 30 -August 4, Volume 1: Long Papers, 2017.","title":"Improved neural relation detection for knowledge base question answering","authors":"Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Cícero Nogueira Dos Santos, Bing Xiang, Bowen Zhou","year":"2017","venue":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}