{"type":"ScholarlyArticle","title":"Weakly Supervised Multi-task Learning for Semantic Parsing","authors":[{"name":"Bo Shao","slug":"bo-shao","given":"Bo","family":"Shao","affiliation":"School of Data and Computer Science , Sun Yat-sen University; Microsoft Research Asia"},{"name":"Yeyun Gong","slug":"yeyun-gong","given":"Yeyun","family":"Gong","affiliation":"Microsoft Research Asia"},{"name":"Junwei Bao","slug":"junwei-bao","given":"Junwei","family":"Bao","affiliation":"Microsoft Research Asia"},{"name":"Jianshu Ji","slug":"jianshu-ji","given":"Jianshu","family":"Ji","affiliation":"Microsoft AI and Research , Redmond WA , USA"},{"name":"Guihong Cao","slug":"guihong-cao","given":"Guihong","family":"Cao","affiliation":"Microsoft AI and Research , Redmond WA , USA"},{"name":"Xiaola Lin","slug":"xiaola-lin","given":"Xiaola","family":"Lin","affiliation":"School of Data and Computer Science , Sun Yat-sen University"},{"name":"Nan Duan","slug":"nan-duan","given":"Nan","family":"Duan","affiliation":"Microsoft Research Asia"}],"abstract":"Semantic parsing is a challenging and important task which aims to convert a natural language sentence to a logical form. Existing neural semantic parsing methods mainly use <question, logical form> (Q-L) pairs to train a sequence-to-sequence model. However, the amount of existing Q-L labeled data is limited and hard to obtain. We propose an effective method which substantially utilizes labeling information from other tasks to enhance the training of a semantic parser. We design a multi-task learning model to train question type classification, entity mention detection together with question semantic parsing using a shared encoder. We propose a weakly supervised learning method to enhance our multi-task learning model with paraphrase data, based on the idea that the paraphrased questions should have the same logical form and question type information. Finally, we integrate the weakly supervised multi-task learning method to an encoder-decoder framework. Experiments on a newly constructed dataset and ComplexWebQuestions show that our proposed method outperforms state-of-the-art methods which demonstrates the effectiveness and robustness of our method.","doi":"10.24963/ijcai.2019/468","url":"https://ijcai.org/proceedings/2019/468","pdf":"https://ijcai.org/proceedings/2019/0468.pdf","markdown":"https://ijcai.org/proceedings/2019/468.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/468","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":"Machine Learning M-Z","track":"Main track","number":468,"pages":{"first":3375,"last":3381},"keywords":["Natural Language Processing: Natural Language Semantics","Machine Learning: Transfer, Adaptation, Multi-task Learning","Natural Language Processing: Tagging, chunking, and parsing"],"videos":[],"references":[{"position":1,"raw":"[Bahdanau et al., 2014] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473, 2014.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"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 EMNLP, 2013.","title":"Semantic parsing on freebase from question-answer pairs","authors":"Jonathan Berant, Andrew Chou, Roy Frostig, Percy Liang","year":"2013","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cai and Yates, 2013] Qingqing Cai and Alexander Yates. Large-scale semantic parsing via schema matching and lexicon extension. In ACL, 2013.","title":"Large-scale semantic parsing via schema matching and lexicon extension","authors":"Yates Cai, Qingqing Cai, Alexander Yates","year":"2013","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cheng and Lapata, 2018] Jianpeng Cheng and Mirella La- pata. Weakly-supervised neural semantic parsing with a generative ranker. arXiv preprint arXiv:1808.07625, 2018.","title":"Jianpeng Cheng and Mirella Lapata. Weakly-supervised neural semantic parsing with a generative ranker","authors":"Lapata Cheng","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dong and Lapata, 2016] Li Dong and Mirella Lapata. Lan- guage to logical form with neural attention. In ACL, 2016.","title":"Language to logical form with neural attention","authors":"Li Dong, Mirella Lapata","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dong and Lapata, 2018] Li Dong and Mirella Lapata. Coarse-to-fine decoding for neural semantic parsing. arXiv preprint arXiv:1805.04793, 2018.","title":"Coarse-to-fine decoding for neural semantic parsing","authors":"Li Dong, Mirella Lapata","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fader et al., 2013] Anthony Fader, Luke Zettlemoyer, and Oren Etzioni. Paraphrase-driven learning for open ques- tion answering. In ACL, 2013.","title":"Paraphrase-driven learning for open question answering","authors":"Anthony Fader, Luke Zettlemoyer, Oren Etzioni","year":"2013","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fan et al., 2017] Xing Fan, Emilio Monti, Lambert Mathias, and Markus Dreyer. Transfer learning for neural semantic parsing. arXiv preprint arXiv:1706.04326, 2017.","title":"Transfer learning for neural semantic parsing","authors":"Xing Fan, Emilio Monti, Lambert Mathias, Markus Dreyer","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Goldman et al., 2018] Omer Goldman, Veronica Latcin- nik, Ehud Nave, Amir Globerson, and Jonathan Berant. Weakly supervised semantic parsing with abstract exam- ples. In ACL, 2018.","title":"Weakly supervised semantic parsing with abstract examples","authors":"Omer Goldman, Veronica Latcinnik, Ehud Nave, Jonathan Amir Globerson, Berant","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gu et al., 2016] Jiatao Gu, Zhengdong Lu, Hang Li, and Victor OK Li. Incorporating copying mecha- nism in sequence-to-sequence learning. arXiv preprint arXiv:1603.06393, 2016.","title":"Incorporating copying mechanism in sequence-to-sequence learning","authors":"Gu","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Guo et al., 2018] Han Guo, Ramakanth Pasunuru, and Mo- hit Bansal. Soft layer-specific multi-task summarization with entailment and question generation. arXiv preprint arXiv:1805.11004, 2018.","title":"Soft layer-specific multi-task summarization with entailment and question generation","authors":"Han Guo, Ramakanth Pasunuru, Mohit Bansal","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Jia and Liang, 2016] Robin Jia and Percy Liang. Data re- combination for neural semantic parsing. In ACL, 2016.","title":"Data recombination for neural semantic parsing","authors":"Liang Jia, Robin Jia, Percy Liang","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kullback, 1997] Solomon Kullback. Information theory and statistics. Courier Corporation, 1997.","title":"Information theory and statistics","authors":"Kullback","year":"1997","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kwiatkowski et al., 2011] Tom Kwiatkowski, Luke Zettle- moyer, Sharon Goldwater, and Mark Steedman. Lexi- cal generalization in ccg grammar induction for semantic parsing. In EMNLP, 2011.","title":"Lexical generalization in ccg grammar induction for semantic parsing","authors":"Kwiatkowski","year":"2011","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lee et al., 2016] Kenton Lee, Mike Lewis, and Luke Zettle- moyer. Global neural ccg parsing with optimality guaran- tees. arXiv preprint arXiv:1607.01432, 2016.","title":"Global neural ccg parsing with optimality guarantees","authors":"Kenton Lee, Mike Lewis, Luke Zettlemoyer","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lin et al., 2018] Ying Lin, Shengqi Yang, Veselin Stoyanov, and Heng Ji. A multi-lingual multi-task architecture for low-resource sequence labeling. In ACL, 2018.","title":"A multi-lingual multi-task architecture for low-resource sequence labeling","authors":"Ying Lin, Shengqi Yang, Veselin Stoyanov, Heng Ji","year":"2018","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Liu et al., 2017] Pengfei Liu, Xipeng Qiu, and Xuanjing Huang. Adversarial multi-task learning for text classifi- cation. arXiv preprint arXiv:1704.05742, 2017.","title":"Adversarial multi-task learning for text classification","authors":"Pengfei Liu, Xipeng Qiu, Xuanjing Huang","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Papineni et al., 2002] Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. Bleu: a method for au- tomatic evaluation of machine translation. In Proceedings of ACL, pages 311-318, 2002.","title":"Bleu: a method for automatic evaluation of machine translation","authors":"Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu","year":"2002","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Peng et al., 2017] Hao Peng, Sam Thomson, and Noah A Smith. Deep multitask learning for semantic dependency parsing. arXiv preprint arXiv:1704.06855, 2017.","title":"Deep multitask learning for semantic dependency parsing","authors":"Hao Peng, Sam Thomson, Noah A Smith","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher Manning. Glove: Global vectors for word representation. In EMNLP, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher Manning","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rabinovich et al., 2017] Maxim Rabinovich, Mitchell Stern, and Dan Klein. Abstract syntax networks for code generation and semantic parsing. arXiv preprint arXiv:1704.07535, 2017.","title":"Abstract syntax networks for code generation and semantic parsing","authors":"Rabinovich","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[See et al., 2017] Abigail See, Peter J Liu, and Christopher D Manning. Get to the point: Summarization with pointer- generator networks. arXiv preprint arXiv:1704.04368, 2017.","title":"Get to the point: Summarization with pointergenerator networks","authors":"Abigail See, Peter J Liu, Christopher D Manning","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Su and Yan, 2017] Yu Su and Xifeng Yan. Cross-domain semantic parsing via paraphrasing. arXiv preprint arXiv:1704.05974, 2017.","title":"Cross-domain semantic parsing via paraphrasing","authors":"Yu Su, Xifeng Yan","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Talmor and Berant, 2018] Alon Talmor and Jonathan Be- rant. The web as a knowledge-base for answering complex questions. arXiv preprint arXiv:1803.06643, 2018.","title":"The web as a knowledge-base for answering complex questions","authors":"Alon Talmor, Jonathan Berant","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Trivedi et al., 2017] Priyansh Trivedi, Gaurav Maheshwari, Mohnish Dubey, and Jens Lehmann. Lc-quad: A corpus for complex question answering over knowledge graphs. In International Semantic Web Conference, pages 210- 218. Springer, 2017.","title":"Lc-quad: A corpus for complex question answering over knowledge graphs","authors":"Trivedi","year":"2017","venue":"International Semantic Web Conference","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Unger et al., 2016] Christina Unger, Axel-Cyrille Ngonga Ngomo, and Elena Cabrio. 6th open challenge on ques- tion answering over linked data (qald-6). In Semantic Web Evaluation Challenge, pages 171-177. Springer, 2016.","title":"6th open challenge on question answering over linked data (qald-6)","authors":"Christina Unger, Axel-Cyrille Ngonga Ngomo, Elena Cabrio","year":"2016","venue":"Semantic Web Evaluation Challenge","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Wang et al., 2018] Yizhong Wang, Kai Liu, Jing Liu, Wei He, Yajuan Lyu, Hua Wu, Sujian Li, and Haifeng Wang. Multi-passage machine reading comprehension with cross-passage answer verification. arXiv preprint arXiv:1805.02220, 2018.","title":"Multi-passage machine reading comprehension with cross-passage answer verification","authors":"Yizhong Wang, Kai Liu, Jing Liu, Wei He, Yajuan Lyu, Hua Wu, Sujian Li, Haifeng Wang","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zettlemoyer and Collins, 2007] Luke Zettlemoyer and Michael Collins. Online learning of relaxed ccg grammars for parsing to logical form. In EMNLP-CoNLL, 2007.","title":"Online learning of relaxed ccg grammars for parsing to logical form","authors":"Collins ; Zettlemoyer, Luke Zettlemoyer, Michael Collins","year":"2007","venue":"EMNLP-CoNLL","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zettlemoyer and Collins, 2012] Luke S Zettlemoyer and Michael Collins. Learning to map sentences to logical form: Structured classification with probabilistic catego- rial grammars. arXiv preprint arXiv:1207.1420, 2012.","title":"Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars","authors":"Collins ; Zettlemoyer, S Luke, Michael Zettlemoyer, Collins","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhang et al., 2017] Yuchen Zhang, Panupong Pasupat, and Percy Liang. Macro grammars and holistic trigger- ing for efficient semantic parsing. arXiv preprint arXiv:1707.07806, 2017.","title":"Macro grammars and holistic triggering for efficient semantic parsing","authors":"Yuchen Zhang, Panupong Pasupat, Percy Liang","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhong et al., 2017] Victor Zhong, Caiming Xiong, and Richard Socher. Seq2sql: Generating structured queries from natural language using reinforcement learning. CoRR, abs/1709.00103, 2017.","title":"Seq2sql: Generating structured queries from natural language using reinforcement learning","authors":"Victor Zhong, Caiming Xiong, Richard Socher","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}