{"type":"ScholarlyArticle","title":"Learning to Select Knowledge for Response Generation in Dialog Systems","authors":[{"name":"Rongzhong Lian","slug":"rongzhong-lian","given":"Rongzhong","family":"Lian","affiliation":"Baidu Inc. , China"},{"name":"Min Xie","slug":"min-xie","given":"Min","family":"Xie","affiliation":"The Hong Kong University of Science and Technology"},{"name":"Fan Wang","slug":"fan-wang","given":"Fan","family":"Wang","affiliation":"Baidu Inc. , China"},{"name":"Jinhua Peng","slug":"jinhua-peng","given":"Jinhua","family":"Peng","affiliation":"Baidu Inc. , China"},{"name":"Hua Wu","slug":"hua-wu","given":"Hua","family":"Wu","affiliation":"Baidu Inc. , China"}],"abstract":"End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However,  few previous work has focused on selecting appropriate knowledge in the learning process. The inappropriate selection of knowledge could prohibit the model from learning to make full use of the knowledge. Motivated by this, we propose an end-to-end neural model which employs a novel knowledge selection mechanism where both prior and posterior distributions over knowledge are used to facilitate knowledge selection. Specifically, a posterior distribution over knowledge is inferred from both utterances and responses, and it ensures the appropriate selection of knowledge during the training process. Meanwhile, a prior distribution, which is inferred from utterances only,  is used to approximate the posterior distribution so that appropriate knowledge can be selected even without responses during the inference process. Compared with the previous work, our model can better incorporate appropriate knowledge in response generation. Experiments on both automatic and human evaluation verify the superiority of our model over previous baselines.","doi":"10.24963/ijcai.2019/706","url":"https://ijcai.org/proceedings/2019/706","pdf":"https://ijcai.org/proceedings/2019/0706.pdf","markdown":"https://ijcai.org/proceedings/2019/706.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/706","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":706,"pages":{"first":5081,"last":5087},"keywords":["Natural Language Processing: Natural Language Generation","Natural Language Processing: Dialogue"],"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":"[Cho et al., 2014a] Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, and Yoshua Bengio. On the proper- ties of neural machine translation: Encoder-decoder ap- proaches. In Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation, pages 103-111, 2014.","title":"On the properties of neural machine translation: Encoder-decoder approaches","authors":"Cho","year":"2014","venue":"Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cho et al., 2014b] 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 Proceedings of the 2014 Confer- ence on Empirical Methods in Natural Language Process- ing, pages 1724-1734, 2014.","title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Dinan et al., 2018] Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. Wizard of wikipedia: Knowledge-powered conversational agents. arXiv preprint arXiv:1811.01241, 2018.","title":"Wizard of wikipedia: Knowledge-powered conversational agents","authors":"Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, Jason Weston","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Dinan et al., 2019] Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe, et al. The second conversational intelligence challenge. arXiv preprint arXiv:1902.00098, 2019.","title":"The second conversational intelligence challenge","authors":"Emily Dinan, Varvara Logacheva, Valentin Malykh, Alexander Miller, Kurt Shuster, Jack Urbanek, Douwe Kiela, Arthur Szlam, Iulian Serban, Ryan Lowe","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fleiss, 1971] Joseph L Fleiss. Measuring nominal scale agreement among many raters. Psychological bulletin, page 378, 1971.","title":"Measuring nominal scale agreement among many raters","authors":"L Joseph, Fleiss","year":"1971","venue":"Psychological bulletin","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ghazvininejad et al., 2018] Marjan Ghazvininejad, Chris Brockett, Ming-Wei Chang, Bill Dolan, Jianfeng Gao, Wen-tau Yih, and Michel Galley. A knowledge-grounded neural conversation model. In Thirty-Second AAAI Con- ference on Artificial Intelligence, 2018.","title":"A knowledge-grounded neural conversation model","authors":"Marjan Ghazvininejad, Chris Brockett, Ming-Wei Chang, Bill Dolan, Jianfeng Gao, Wen-Tau Yih, Michel Galley","year":"2018","venue":"Thirty-Second AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gu et al., 2016] Jiatao Gu, Zhengdong Lu, Hang Li, and Victor O. K. Li. Incorporating copying mechanism in sequence-to-sequence learning. In Proceedings of the 54th Annual Meeting of the Association for Computational Lin- guistics, 2016.","title":"Incorporating copying mechanism in sequence-to-sequence learning","authors":"Gu","year":"2016","venue":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jang et al., 2016] Eric Jang, Shixiang Gu, and Ben Poole. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144, 2016.","title":"Categorical reparameterization with gumbel-softmax","authors":"Eric Jang, Shixiang Gu, Ben Poole","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Li et al., 2016] Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity-promoting ob- jective function for neural conversation models. In The 2016 Conference of the North American Chapter of the As- sociation for Computational Linguistics, pages 110-119, 2016.","title":"A diversity-promoting objective function for neural conversation models","authors":"Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, Bill Dolan","year":"2016","venue":"The 2016 Conference of the North American Chapter of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2018] Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, and Dawei Yin. Knowledge diffusion for neural dialogue generation. In Proceedings of the 56th Annual Meeting of the Association for Compu- tational Linguistics, pages 1489-1498, 2018.","title":"Knowledge diffusion for neural dialogue generation","authors":"Shuman Liu, Hongshen Chen, Zhaochun Ren, Yang Feng, Qun Liu, Dawei Yin","year":"2018","venue":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Long et al., 2017] Yinong Long, Jianan Wang, Zhen Xu, Zongsheng Wang, Baoxun Wang, and Zhuoran Wang. A knowledge enhanced generative conversational service agent. In Proceedings of the 6th Dialog System Technol- ogy Challenges (DSTC6) Workshop, 2017.","title":"A knowledge enhanced generative conversational service agent","authors":"Long","year":"2017","venue":"Proceedings of the 6th Dialog System Technology Challenges (DSTC6) Workshop","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Pennington et al., 2014] Jeffrey Pennington, Richard Socher, and Christopher Manning. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing, pages 1532-1543, 2014.","title":"Glove: Global vectors for word representation","authors":"Jeffrey Pennington, Richard Socher, Christopher Manning","year":"2014","venue":"Proceedings of the 2014 conference on empirical methods in natural language processing","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Shang et al., 2015] Lifeng Shang, Zhengdong Lu, and Hang Li. Neural responding machine for short-text conversation. In Proceedings of the 53rd Annual Meeting of the Associ- ation for Computational Linguistics and the 7th Interna- tional Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, pages 1577-1586, 2015.","title":"Neural responding machine for short-text conversation","authors":"Lifeng Shang, Zhengdong Lu, Hang Li","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","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Vinyals and Le, 2015] Oriol Vinyals and Quoc Le. A neural conversational model. arXiv preprint arXiv:1506.05869, 2015.","title":"Oriol Vinyals and Quoc Le. A neural conversational model","authors":"Le Vinyals","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Xu et al., 2017] Zhen Xu, Bingquan Liu, Baoxun Wang, Chengjie Sun, and Xiaolong Wang. Incorporating loose- structured knowledge into conversation modeling via recall-gate LSTM. In 2017 International Joint Conference on Neural Networks, pages 3506-3513, 2017.","title":"Incorporating loosestructured knowledge into conversation modeling via recall-gate LSTM","authors":"Zhen Xu, Bingquan Liu, Baoxun Wang, Chengjie Sun, Xiaolong Wang","year":"2017","venue":"2017 International Joint Conference on Neural Networks","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Yao et al., 2017] Lili Yao, Yaoyuan Zhang, Yansong Feng, Dongyan Zhao, and Rui Yan. Towards implicit content- introducing for generative short-text conversation systems. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2190- 2199, 2017.","title":"Towards implicit contentintroducing for generative short-text conversation systems","authors":"Lili Yao, Yaoyuan Zhang, Yansong Feng, Dongyan Zhao, Rui Yan","year":"2017","venue":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Zhang et al., 2018] Saizheng Zhang, Emily Dinan, Jack Ur- banek, Arthur Szlam, Douwe Kiela, and Jason Weston. Personalizing dialogue agents: I have a dog, do you have pets too? In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pages 2204- 2213, 2018.","title":"Personalizing dialogue agents: I have a dog, do you have pets too?","authors":"Zhang","year":"2018","venue":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Zhao et al., 2017] Tiancheng Zhao, Ran Zhao, and Maxine Eskénazi. Learning discourse-level diversity for neural di- alog models using conditional variational autoencoders. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pages 654-664, 2017.","title":"Learning discourse-level diversity for neural dialog models using conditional variational autoencoders","authors":"Zhao","year":"2017","venue":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Zhou et al., 2018] Hao Zhou, Tom Young, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. Com- monsense knowledge aware conversation generation with graph attention. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pages 4623-4629, 2018.","title":"Commonsense knowledge aware conversation generation with graph attention","authors":"Hao Zhou, Tom Young, Minlie Huang, Haizhou Zhao, Jingfang Xu, Xiaoyan Zhu","year":"2018","venue":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/643"},{"position":21,"raw":"[Zhu et al., 2017] Wenya Zhu, Kaixiang Mo, Yu Zhang, Zhangbin Zhu, Xuezheng Peng, and Qiang Yang. Flex- ible end-to-end dialogue system for knowledge grounded conversation. arXiv preprint arXiv:1709.04264, 2017.","title":"Flexible end-to-end dialogue system for knowledge grounded conversation","authors":"Wenya Zhu, Kaixiang Mo, Yu Zhang, Zhangbin Zhu, Xuezheng Peng, Qiang Yang","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}