{"type":"ScholarlyArticle","title":"Learning Out-of-Vocabulary Words in Intelligent Personal Agents","authors":[{"name":"Avik Ray","slug":"avik-ray","given":"Avik","family":"Ray","affiliation":"Samsung Research America , Mountain View , California , USA"},{"name":"Yilin Shen","slug":"yilin-shen","given":"Yilin","family":"Shen","affiliation":"Samsung Research America , Mountain View , California , USA"},{"name":"Hongxia Jin","slug":"hongxia-jin","given":"Hongxia","family":"Jin","affiliation":"Samsung Research America , Mountain View , California , USA"}],"abstract":"Semantic parsers play a vital role in intelligent agents to convert natural language instructions to an actionable logical form representation. However, after deployment, these parsers suffer from poor accuracy on encountering out-of-vocabulary (OOV) words, or significant accuracy drop on previously supported instructions after retraining. Achieving both goals simultaneously is non-trivial. In this paper, we propose novel neural networks based parsers to learn OOV words; one incorporating a new hybrid paraphrase generation model, and an enhanced sequence-to-sequence model. Extensive experiments on both benchmark and custom datasets show our new parsers achieve significant accuracy gain on OOV words and phrases, and in the meanwhile learn OOV words while maintaining accuracy on previously supported instructions.","doi":"10.24963/ijcai.2018/599","url":"https://ijcai.org/proceedings/2018/599","pdf":"https://ijcai.org/proceedings/2018/0599.pdf","markdown":"https://ijcai.org/proceedings/2018/599.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/599","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Natural Language Processing","track":"Main track","number":599,"pages":{"first":4309,"last":4315},"keywords":["Natural Language Processing: NLP Applications and Tools","Machine Learning: Neural Networks","Natural Language Processing: Natural Language Semantics","Machine Learning: Deep Learning"],"videos":[],"references":[{"position":1,"raw":"[Artzi and Zettlemoyer, 2013] Yoav Artzi and Luke Zettlemoyer. Weakly supervised learning of semantic parsers for mapping in- structions to actions. TACL, 1:49-62, 2013.","title":"Weakly supervised learning of semantic parsers for mapping instructions to actions","authors":"Zettlemoyer Artzi, Yoav Artzi, Luke Zettlemoyer","year":"2013","venue":"TACL","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Azaria et al., 2016] Amos Azaria, Jayant Krishnamurthy, and Tom M Mitchell. Instructable intelligent personal agent. In Proc. of the 30th AAAI, pages 2681-2689, 2016.","title":"Instructable intelligent personal agent","authors":"Amos Azaria, Jayant Krishnamurthy, Tom M Mitchell","year":"2016","venue":"Proc. of the 30th AAAI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bahdanau et al., 2015] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate. In Proceedings of the ICLR, San Diego, California, 2015.","title":"Neural machine translation by jointly learning to align and translate","authors":"Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio","year":"2015","venue":"Proceedings of the ICLR","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Berant and Liang, 2014] Jonathan Berant and Percy Liang. Se- mantic parsing via paraphrasing. In Proc. of ACL (1), pages 1415-1425, 2014.","title":"Semantic parsing via paraphrasing","authors":"Liang Berant, Jonathan Berant, Percy Liang","year":"2014","venue":"Proc. of ACL (1)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bobrow, 1964] Daniel G Bobrow. Natural language input for a computer problem solving system. In Proc., Fall Joint Comput. Conf. 25 (1964). Also available as Ph.D. Thesis, Math. Dept., MIT, Cambridge, Mass., 1964.","title":"Natural language input for a computer problem solving system","authors":"G Daniel, Bobrow","year":"1964","venue":"Proc., Fall Joint Comput. Conf. 25","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart van Merrienboer, C ¸aglar Gülc ¸ehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In Proc. of the 2014 EMNLP, pages 1724-1734, 2014.","title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"Proc. of the 2014 EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dong and Lapata, 2016] Li Dong and Mirella Lapata. Language to logical form with neural attention. In Proc. of the 54th ACL 2016, 2016.","title":"Language to logical form with neural attention","authors":"Li Dong, Mirella Lapata","year":"2016","venue":"Proc. of the 54th ACL 2016","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dong et al., 2017] Li Dong, Jonathan Mallinson, Siva Reddy, and Mirella Lapata. Learning to paraphrase for question answering. In Proc. of EMNLP 2017, pages 875-886, 2017.","title":"Learning to paraphrase for question answering","authors":"Li Dong, Jonathan Mallinson, Siva Reddy, Mirella Lapata","year":"2017","venue":"Proc. of EMNLP 2017","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jia and Liang, 2016] Robin Jia and Percy Liang. Data recombina- tion for neural semantic parsing. In Proc. of the 54th ACL, 2016.","title":"Data recombination for neural semantic parsing","authors":"Liang ; ] Jia, Robin Jia, Percy Liang","year":"2016","venue":"Proc. of the 54th ACL","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Karpathy and Fei-Fei, 2017] Andrej Karpathy and Li Fei-Fei. Deep visual-semantic alignments for generating image descrip- tions. IEEE Trans. Pattern Anal. Mach. Intell., 39(4):664-676, 2017.","title":"Deep visual-semantic alignments for generating image descriptions","authors":"Fei-Fei ; Karpathy, Andrej Karpathy, Li Fei-Fei","year":"2017","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kiddon et al., 2016] Chloé Kiddon, Luke S. Zettlemoyer, and Yejin Choi. Globally coherent text generation with neural check- list models. In Proc. of EMNLP, 2016.","title":"Globally coherent text generation with neural checklist models","authors":"Chloé Kiddon, Luke S Zettlemoyer, Yejin Choi","year":"2016","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Krishnamurthy, 2016] Jayant Krishnamurthy. Probabilistic models for learning a semantic parser lexicon. In Proceedings of NAACL- HLT, pages 606-616, 2016.","title":"Probabilistic models for learning a semantic parser lexicon","authors":"Jayant Krishnamurthy","year":"2016","venue":"Proceedings of NAACL-HLT","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kwiatkowski et al., 2011] Tom Kwiatkowski, Luke Zettlemoyer, Sharon Goldwater, and Mark Steedman. Lexical generalization in ccg grammar induction for semantic parsing. In Proc. of EMNLP, 2011, pages 1512-1523. ACL, 2011.","title":"Lexical generalization in ccg grammar induction for semantic parsing","authors":"Kwiatkowski","year":"2011","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Luong and Manning, 2016] Minh-Thang Luong and Christo- pher D. Manning. Achieving open vocabulary neural machine translation with hybrid word-character models. In Proc. of the 54th ACL 2016, 2016.","title":"Achieving open vocabulary neural machine translation with hybrid word-character models","authors":"Minh-Thang Luong, Christopher D Manning","year":"2016","venue":"Proc. of the 54th ACL 2016","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Luong et al., 2015] Thang Luong, Ilya Sutskever, Quoc V. Le, Oriol Vinyals, and Wojciech Zaremba. Addressing the rare word problem in neural machine translation. In Proceedings of ACL 2015, pages 11-19, 2015.","title":"Addressing the rare word problem in neural machine translation","authors":"Thang Luong, Ilya Sutskever, Quoc V Le, Oriol Vinyals, Wojciech Zaremba","year":"2015","venue":"Proceedings of ACL 2015","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Mikolov et al., 2013] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. CoRR, 2013.","title":"Efficient estimation of word representations in vector space","authors":"Tomas Mikolov, Kai Chen, Greg Corrado, Jeffrey Dean","year":"2013","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher D. Manning. Glove: Global vectors for word repre- sentation. In Empirical Methods in Natural Language Processing (EMNLP), pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher D Manning","year":"2014","venue":"Empirical Methods in Natural Language Processing (EMNLP)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Prakash et al., 2016] Aaditya Prakash, Sadid A. Hasan, Kathy Lee, Vivek V. Datla, Ashequl Qadir, Joey Liu, and Oladimeji Farri. Neural paraphrase generation with stacked residual LSTM net- works. In Proc. of COLING 2016, pages 2923-2934, 2016.","title":"Neural paraphrase generation with stacked residual LSTM networks","authors":"Aaditya Prakash, Sadid A Hasan, Kathy Lee, V Vivek, Ashequl Datla, Joey Qadir, Oladimeji Liu, Farri","year":"2016","venue":"Proc. of COLING 2016","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Rush et al., 2015] Alexander M. Rush, Sumit Chopra, and Jason Weston. A neural attention model for abstractive sentence sum- marization. In Proc. of the 2015 EMNLP, pages 379-389, 2015.","title":"A neural attention model for abstractive sentence summarization","authors":"Alexander M Rush, Sumit Chopra, Jason Weston","year":"2015","venue":"Proc. of the 2015 EMNLP","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. In Proc. of NIPS, pages 3104-3112, 2014.","title":"Quoc V Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"Proc. of NIPS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Thomason et al., 2015] Jesse Thomason, Shiqi Zhang, Ray- mond J. Mooney, and Peter Stone. Learning to interpret natu- ral language commands through human-robot dialog. In Proc. of IJCAI 2015,, pages 1923-1929, 2015.","title":"Learning to interpret natural language commands through human-robot dialog","authors":"Jesse Thomason, Shiqi Zhang, Raymond J Mooney, Peter Stone","year":"2015","venue":"Proc. of IJCAI 2015","doi":null,"url":null,"internal_url":"/proceedings/2015/273"},{"position":22,"raw":"[Vinyals et al., 2015a] Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. Pointer networks. In Proc. of NIPS, pages 2692-2700, 2015.","title":"Pointer networks","authors":"Vinyals","year":"2015","venue":"Proc. of NIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vinyals et al., 2015b] Oriol Vinyals, Lukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey E. Hinton. Grammar as a foreign language. In Proc. of NIPS, pages 2773-2781, 2015.","title":"Grammar as a foreign language","authors":"Vinyals","year":"2015","venue":"Proc. of NIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wong and Mooney, 2007] Yuk Wah Wong and Raymond J Mooney. Learning synchronous grammars for semantic parsing with lambda calculus. In ACL, volume 45, page 960, 2007.","title":"Learning synchronous grammars for semantic parsing with lambda calculus","authors":"Mooney ; ] Wong, Wah Yuk, Raymond J Wong, Mooney","year":"2007","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zelle and Mooney, 1996] John M Zelle and Raymond J Mooney. Learning to parse database queries using inductive logic pro- gramming. In Proceedings of the national conference on artificial intelligence, pages 1050-1055, 1996.","title":"Learning to parse database queries using inductive logic programming","authors":"M John, Raymond J Zelle, Mooney","year":"1996","venue":"Proceedings of the national conference on artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zettlemoyer and Collins, 2005] Luke S Zettlemoyer and Michael Collins. Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars. In Proceed- ings of the 21st UAI, pages 658-666, 2005.","title":"Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars","authors":"Collins ; Zettlemoyer, S Luke, Michael Zettlemoyer, Collins","year":"2005","venue":"Proceedings of the 21st UAI","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zettlemoyer and Collins, 2007] Luke S Zettlemoyer and Michael Collins. Online learning of relaxed ccg grammars for parsing to logical form. In EMNLP-CoNLL, pages 678-687, 2007.","title":"Online learning of relaxed ccg grammars for parsing to logical form","authors":"Collins ; Zettlemoyer, S Luke, Michael Zettlemoyer, Collins","year":"2007","venue":"EMNLP-CoNLL","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhao et al., 2009] Shiqi Zhao, Xiang Lan, Ting Liu, and Sheng Li. Application-driven statistical paraphrase generation. In Proc. of the 47th ACL and 4th IJCNLP-AFNLP, pages 834-842. Associ- ation for Computational Linguistics, 2009.","title":"Application-driven statistical paraphrase generation","authors":"Shiqi Zhao, Xiang Lan, Ting Liu, Sheng Li","year":"2009","venue":"Proc. of the 47th ACL and 4th IJCNLP-AFNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}