{"type":"ScholarlyArticle","title":"Retrieve, Program, Repeat: Complex Knowledge Base Question Answering via Alternate Meta-learning","authors":[{"name":"Yuncheng Hua","slug":"yuncheng-hua","given":"Yuncheng","family":"Hua","affiliation":"School of Computer Science and Engineering , Southeast University , Nanjing , China; Southeast University-Monash University Joint Research Institute , Suzhou , China"},{"name":"Yuan-Fang Li","slug":"yuan-fang-li","given":"Yuan-Fang","family":"Li","affiliation":"Faculty of Information Technology , Monash University , Melbourne , Australia"},{"name":"Gholamreza Haffari","slug":"gholamreza-haffari","given":"Gholamreza","family":"Haffari","affiliation":"Faculty of Information Technology , Monash University , Melbourne , Australia"},{"name":"Guilin Qi","slug":"guilin-qi","given":"Guilin","family":"Qi","affiliation":"School of Computer Science and Engineering , Southeast University , Nanjing , China; Key Laboratory of Computer Network and Information Integration , Southeast University , China"},{"name":"Wei Wu","slug":"wei-wu","given":"Wei","family":"Wu","affiliation":"School of Computer Science and Engineering , Southeast University , Nanjing , China"}],"abstract":"A compelling approach to complex question answering is to convert the question to a sequence of actions, which can then be executed on the knowledge base to yield the answer, aka the programmer-interpreter approach. Use similar training questions to the test question, meta-learning enables the programmer to adapt to unseen questions to tackle potential distributional biases quickly. However, this comes at the cost of manually labeling similar questions to learn a retrieval model, which is tedious and expensive. In this paper, we present a novel method that automatically learns a retrieval model alternately with the programmer from weak supervision, i.e., the system’s performance with respect to the produced answers. To the best of our knowledge, this is the first attempt to train the retrieval model with the programmer jointly. Our system leads to state-of-the-art performance on a large-scale task for complex question answering over knowledge bases. We have released our code at https://github.com/DevinJake/MARL.","doi":"10.24963/ijcai.2020/509","url":"https://ijcai.org/proceedings/2020/509","pdf":"https://ijcai.org/proceedings/2020/0509.pdf","markdown":"https://ijcai.org/proceedings/2020/509.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/509","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Natural Language Processing","track":"Main track","number":509,"pages":{"first":3679,"last":3686},"keywords":["Natural Language Processing: Question Answering","Natural Language Processing: Natural Language Processing"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24776/file_24776.m3u8","length_sec":305,"provider":"hls"}],"references":[{"position":1,"raw":"[Ansari et al., 2019] Ghulam Ahmed Ansari, Amrita Saha, Vishwajeet Kumar, Mohan Bhambhani, Karthik Sankara- narayanan, and Soumen Chakrabarti. Neural program in- duction for kbqa without gold programs or query annota- tions. In Proceedings of the 28th International Joint Con- ference on Artificial Intelligence, pages 4890-4896. AAAI Press, 2019.","title":"Neural program induction for kbqa without gold programs or query annotations","authors":"Ghulam Ahmed Ansari, Amrita Saha, Vishwajeet Kumar, Mohan Bhambhani, Karthik Sankaranarayanan, Soumen Chakrabarti","year":"2019","venue":"Proceedings of the 28th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2019/679"},{"position":2,"raw":"[Berant et al., 2013] Jonathan Berant, Andrew Chou, Roy Frostig, and Percy Liang. Semantic parsing on freebase from question-answer pairs. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1533-1544, 2013.","title":"Semantic parsing on freebase from question-answer pairs","authors":"Jonathan Berant, Andrew Chou, Roy Frostig, Percy Liang","year":"2013","venue":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bordes et al., 2015] Antoine Bordes, Nicolas Usunier, Sumit Chopra, and Jason Weston. Large-scale simple question answering with memory networks. arXiv preprint arXiv:1506.02075, 2015.","title":"Large-scale simple question answering with memory networks","authors":"Antoine Bordes, Nicolas Usunier, Sumit Chopra, Jason Weston","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Finn et al., 2017] Chelsea Finn, Pieter Abbeel, and Sergey Levine. Model-agnostic meta-learning for fast adaptation of deep networks. In Proceedings of the 34th International Conference on Machine Learning-Volume 70, pages 1126- 1135. JMLR. org, 2017.","title":"Model-agnostic meta-learning for fast adaptation of deep networks","authors":"Finn","year":"2017","venue":"Proceedings of the 34th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Guo et al., 2018] Daya Guo, Duyu Tang, Nan Duan, Ming Zhou, and Jian Yin. Dialog-to-action: conversational ques- tion answering over a large-scale knowledge base. In Ad- vances in Neural Information Processing Systems, pages 2942-2951, 2018.","title":"Dialog-to-action: conversational question answering over a large-scale knowledge base","authors":"Duyu Daya Guo, Nan Tang, Ming Duan, Jian Zhou, Yin","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Guo et al., 2019] Daya Guo, Duyu Tang, Nan Duan, Ming Zhou, and Jian Yin. Coupling retrieval and meta- learning for context-dependent semantic parsing. In Anna Korhonen, David R. Traum, and Lluís Màrquez, edi- tors, Proceedings of the 57th Conference of the Associa- tion for Computational Linguistics, ACL 2019, Florence, Italy, July 28-August 2, 2019, Volume 1: Long Papers, pages 855-866. Association for Computational Linguis- tics, 2019.","title":"Coupling retrieval and metalearning for context-dependent semantic parsing","authors":"Duyu Daya Guo, Nan Tang, Ming Duan, Jian Zhou, Yin","year":"2019","venue":"Lluís Màrquez, editors, Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ha et al., 2017] David Ha, Andrew M. Dai, and Quoc V. Le. Hypernetworks. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. Open- Review.net, 2017.","title":"5th International Conference on Learning Representations, ICLR 2017","authors":"David Ha, Andrew M Dai, V Quoc, Le, Hypernetworks","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Huang et al., 2013] Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, and Larry Heck. Learning deep structured semantic models for web search using click- through data. In Proceedings of the 22nd ACM interna- tional conference on Information & Knowledge Manage- ment, pages 2333-2338, 2013.","title":"Learning deep structured semantic models for web search using clickthrough data","authors":"Po-Sen Huang, Xiaodong He, Jianfeng Gao, Li Deng, Alex Acero, Larry Heck","year":"2013","venue":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang et al., 2018] Po-Sen Huang, Chenglong Wang, Rishabh Singh, Wen-tau Yih, and Xiaodong He. Natural language to structured query generation via meta-learning. In Proceedings of the 2018 Conference of the North Amer- ican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 732-738, 2018.","title":"Natural language to structured query generation via meta-learning","authors":"Huang","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":"[Li and Malik, 2017] Ke Li and Jitendra Malik. Learning to optimize neural nets. CoRR, abs/1703.00441, 2017.","title":"Learning to optimize neural nets","authors":"Malik ; Li, Ke Li, Jitendra Malik","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"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 (Volume 1: Long Papers), volume 1, 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","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2019] Shikun Liu, Andrew Davison, and Edward Johns. Self-supervised generalisation with meta auxiliary learning. In Advances in Neural Information Processing Systems, pages 1677-1687, 2019.","title":"Self-supervised generalisation with meta auxiliary learning","authors":"Shikun Liu, Andrew Davison, Edward Johns","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Luo et al., 2019] Liangchen Luo, Yuanhao Xiong, Yan Liu, and Xu Sun. Adaptive gradient methods with dynamic bound of learning rate. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net, 2019.","title":"Adaptive gradient methods with dynamic bound of learning rate","authors":"Luo","year":"2019","venue":"7th International Conference on Learning Representations, ICLR 2019","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Nichol and Schulman, 2018] Alex Nichol and John Schul- man. Reptile: a scalable metalearning algorithm. arXiv preprint arXiv:1803.02999, 2:2, 2018.","title":"Reptile: a scalable metalearning algorithm","authors":"Alex Nichol, John Schulman","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"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 Thirty-Second AAAI Conference on Artificial Intelligence, 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":"Thirty-Second AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Saha et al., 2019] Amrita Saha, Ghulam Ahmed Ansari, Abhishek Laddha, Karthik Sankaranarayanan, and Soumen Chakrabarti. Complex program induction for querying knowledge bases in the absence of gold pro- grams. Transactions of the Association for Computational Linguistics, 7:185-200, 2019.","title":"Complex program induction for querying knowledge bases in the absence of gold programs","authors":"Amrita Saha, Ghulam Ahmed Ansari, Abhishek Laddha, Karthik Sankaranarayanan, Soumen Chakrabarti","year":"2019","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Schmidhuber, 1992] Jürgen Schmidhuber. Learning to con- trol fast-weight memories: An alternative to dynamic re- current networks. Neural Computation, 4(1):131-139, 1992.","title":"Learning to control fast-weight memories: An alternative to dynamic recurrent networks","authors":"Jürgen Schmidhuber","year":"1992","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shen et al., 2019] Tao Shen, Xiubo Geng, Tao QIN, Daya Guo, Duyu Tang, Nan Duan, Guodong Long, and Daxin Jiang. Multi-task learning for conversational question an- swering over a large-scale knowledge base. In Proceedings of the 2019 Conference on Empirical Methods in Natu- ral Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP- IJCNLP), pages 2442-2451, Hong Kong, China, Novem- ber 2019. Association for Computational Linguistics.","title":"Multi-task learning for conversational question answering over a large-scale knowledge base","authors":"Tao Shen, Xiubo Geng, Qin Tao, Daya Guo, Duyu Tang, Nan Duan, Guodong Long, Daxin Jiang","year":"2019","venue":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yih et al., 2014] Wen-tau Yih, Xiaodong He, and Christo- pher Meek. Semantic parsing for single-relation question answering. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), volume 2, pages 643-648, 2014.","title":"Semantic parsing for single-relation question answering","authors":"Wen-Tau Yih, Xiaodong He, Christopher Meek","year":"2014","venue":"Proceedings of the 52nd 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, Cicero dos Santos, Bing Xiang, and Bowen Zhou. Im- proved neural relation detection for knowledge base ques- tion answering. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 571-581, 2017.","title":"Improved neural relation detection for knowledge base question answering","authors":"Mo Yu, Wenpeng Yin, Kazi Saidul Hasan, Bing Cicero Dos Santos, Bowen Xiang, Zhou","year":"2017","venue":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}