{"type":"ScholarlyArticle","title":"Commonsense Knowledge Aware Conversation Generation with Graph Attention","authors":[{"name":"Hao Zhou","slug":"hao-zhou","given":"Hao","family":"Zhou","affiliation":"Conversational AI Group, AI Lab. , Dept. of Computer Science , Tsinghua University Beijing National Research Center for Information Science and Technology , China"},{"name":"Tom Young","slug":"tom-young","given":"Tom","family":"Young","affiliation":"School of Information and Electronics , Beijing Institute of Technology , China"},{"name":"Minlie Huang","slug":"minlie-huang","given":"Minlie","family":"Huang","affiliation":"Conversational AI Group, AI Lab. , Dept. of Computer Science , Tsinghua University Beijing National Research Center for Information Science and Technology , China"},{"name":"Haizhou Zhao","slug":"haizhou-zhao","given":"Haizhou","family":"Zhao","affiliation":"Sogou Inc. , Beijing , China"},{"name":"Jingfang Xu","slug":"jingfang-xu","given":"Jingfang","family":"Xu","affiliation":"Sogou Inc. , Beijing , China"},{"name":"Xiaoyan Zhu","slug":"xiaoyan-zhu","given":"Xiaoyan","family":"Zhu","affiliation":"Conversational AI Group, AI Lab. , Dept. of Computer Science , Tsinghua University Beijing National Research Center for Information Science and Technology , China"}],"abstract":"Commonsense knowledge is vital to many natural language processing tasks. In this paper, we present a novel open-domain conversation generation model to demonstrate how large-scale commonsense knowledge can facilitate language understanding and generation. Given a user post, the model retrieves relevant knowledge graphs from a knowledge base and then encodes the graphs with a static graph attention mechanism, which augments the semantic information of the post and thus supports better understanding of the post. Then, during word generation, the model attentively reads the retrieved knowledge graphs and the knowledge triples within each graph to facilitate better generation through a dynamic graph attention mechanism. This is the first attempt that uses large-scale commonsense knowledge in conversation generation. Furthermore, unlike existing models that use knowledge triples (entities) separately and independently, our model treats each knowledge graph as a whole, which encodes more structured, connected semantic information in the graphs. Experiments show that the proposed model can generate more appropriate and informative responses than state-of-the-art baselines.","doi":"10.24963/ijcai.2018/643","url":"https://ijcai.org/proceedings/2018/643","pdf":"https://ijcai.org/proceedings/2018/0643.pdf","markdown":"https://ijcai.org/proceedings/2018/643.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/643","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":643,"pages":{"first":4623,"last":4629},"keywords":["Natural Language Processing: Natural Language Generation","Natural Language Processing: Natural Language Processing","Natural Language Processing: Dialogue"],"videos":[],"references":[{"position":1,"raw":"[Bahdanau et al., 2014] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine transla- tion by jointly learning to align and translate. CoRR, abs/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":"[Bordes et al., 2013] Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. Translating embeddings for modeling multi-relational data. In NIPS, pages 2787-2795, 2013.","title":"Translating embeddings for modeling multi-relational data","authors":"Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, Oksana Yakhnenko","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":3,"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 EMNLP, pages 1724-1734, 2014.","title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Eggins and Slade, 2005] Suzanne Eggins and Diana Slade. Analysing casual conversation. Equinox Publishing Ltd., 2005.","title":"Analysing casual conversation","authors":"Suzanne Eggins, Diana Slade","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ghazvininejad et al., 2017] Marjan Ghazvininejad, Chris Brockett, Ming-Wei Chang, Bill Dolan, Jianfeng Gao, Wen-tau Yih, and Michel Galley. A knowledge-grounded neural conversation model. CoRR, abs/1702.01932, 2017.","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":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gu et al., 2016] Jiatao Gu, Zhengdong Lu, Hang Li, and Victor OK Li. Incorporating copying mechanism in sequence-to-sequence learning. In ACL, pages 1631-1640, 2016.","title":"Incorporating copying mechanism in sequence-to-sequence learning","authors":"Gu","year":"2016","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Han et al., 2015] Sangdo Han, Jeesoo Bang, Seonghan Ryu, and Gary Geunbae Lee. Exploiting knowledge base to generate responses for natural language dialog listening agents. In SIGDIAL, pages 129-133, 2015.","title":"Exploiting knowledge base to generate responses for natural language dialog listening agents","authors":"Han","year":"2015","venue":"SIGDIAL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Li et al., 2016] Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. A diversity-promoting objective function for neural conversation models. In NAACL, 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":"NAACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lin et al., 2017] Hongyu Lin, Le Sun, and Xianpei Han. Reasoning with heterogeneous knowledge for common- sense machine comprehension. In EMNLP, pages 2032- 2043, 2017.","title":"Reasoning with heterogeneous knowledge for commonsense machine comprehension","authors":"Hongyu Lin, Le Sun, Xianpei Han","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":10,"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 DSTC6 Workshop, 2017.","title":"A knowledge enhanced generative conversational service agent","authors":"Long","year":"2017","venue":"DSTC6 Workshop","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Marková et al., 2007] Ivana Marková, Per Linell, Michèle Grossen, and Anne Salazar Orvig. Dialogue in focus groups: Exploring socially shared knowledge. Equinox publishing, 2007.","title":"Dialogue in focus groups: Exploring socially shared knowledge","authors":"Ivana Marková, Per Linell, Michèle Grossen, Anne Salazar Orvig","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Minsky, 1991] Marvin Minsky. Society of mind: a response to four reviews. Artificial Intelligence, 48(3):371-396, 1991.","title":"Society of mind: a response to four reviews","authors":"Marvin Minsky, Minsky","year":"1991","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Mou et al., 2016] Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, and Zhi Jin. Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation. In COLING, pages 3349-3358, 2016.","title":"Sequence to backward and forward sequences: A content-introducing approach to generative short-text conversation","authors":"Lili Mou, Yiping Song, Rui Yan, Ge Li, Lu Zhang, Zhi Jin","year":"2016","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ritter et al., 2011] Alan Ritter, Colin Cherry, and William B. Dolan. Data-driven response generation in social media. In EMNLP, pages 583-593, 2011.","title":"Data-driven response generation in social media","authors":"Alan Ritter, Colin Cherry, William B Dolan","year":"2011","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Serban et al., 2015] Iulian Vlad Serban, Alessandro Sor- doni, Yoshua Bengio, Aaron C. Courville, and Joelle Pineau. Hierarchical neural network generative models for movie dialogues. CoRR, abs/1507.04808, 2015.","title":"Hierarchical neural network generative models for movie dialogues","authors":"Iulian Vlad Serban, Alessandro Sordoni, Yoshua Bengio, Aaron C Courville, Joelle Pineau","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Shang et al., 2015] Lifeng Shang, Zhengdong Lu, and Hang Li. Neural responding machine for short-text conversation. In ACL, pages 1577-1586, 2015.","title":"Neural responding machine for short-text conversation","authors":"Lifeng Shang, Zhengdong Lu, Hang Li","year":"2015","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Shao et al., 2017] Louis Shao, Stephan Gouws, Denny Britz, Anna Goldie, Brian Strope, and Ray Kurzweil. Gen- erating long and diverse responses with neural conversa- tion models. CoRR, abs/1701.03185, 2017.","title":"Generating long and diverse responses with neural conversation models","authors":"Louis Shao, Stephan Gouws, Denny Britz, Anna Goldie, Brian Strope, Ray Kurzweil","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sordoni et al., 2015] Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, and Bill Dolan. A neural network approach to context-sensitive generation of conversational responses. In NAACL, pages 196-205, 2015.","title":"A neural network approach to context-sensitive generation of conversational responses","authors":"Alessandro Sordoni, Michel Galley, Michael Auli, Chris Brockett, Yangfeng Ji, Margaret Mitchell, Jian-Yun Nie, Jianfeng Gao, Bill Dolan","year":"2015","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Souto, 2015] Patrícia Cristina Nascimento Souto. Creating knowledge with and from the differences: the required di- alogicality and dialogical competences. RAI Revista de Administrac ¸ão e Inovac ¸ão, 12(2):60-89, 2015.","title":"Creating knowledge with and from the differences: the required dialogicality and dialogical competences","authors":"Patrícia Cristina, Nascimento Souto","year":"2015","venue":"RAI Revista de Administrac ¸ão e Inovac ¸ão","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Speer and Havasi, 2012] Robert Speer and Catherine Havasi. Representing general relational knowledge in conceptnet 5. In LREC, pages 3679-3686, 2012.","title":"Representing general relational knowledge in conceptnet 5","authors":"Havasi Speer, Robert Speer, Catherine Havasi","year":"2012","venue":"LREC","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sutskever et al., 2014] Ilya Sutskever, Oriol Vinyals, and Quoc V Le. Sequence to sequence learning with neural networks. In NIPS, pages 3104-3112, 2014.","title":"Quoc V Le. Sequence to sequence learning with neural networks","authors":"Sutskever","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Velickovic et al., 2017] Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. CoRR, abs/1710.10903, 2017.","title":"Graph attention networks","authors":"Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, Yoshua Bengio","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wang et al., 2017] Bingning Wang, Kang Liu, and Jun Zhao. Conditional generative adversarial networks for commonsense machine comprehension. In IJCAI, pages 4123-4129, 2017.","title":"Conditional generative adversarial networks for commonsense machine comprehension","authors":"Wang","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/576"},{"position":24,"raw":"[Xing et al., 2017] Chen Xing, Wei Wu, Yu Wu, Jie Liu, Yalou Huang, Ming Zhou, and Wei-Ying Ma. Topic aware neural response generation. In AAAI, pages 3351-3357, 2017.","title":"Topic aware neural response generation","authors":"Chen Xing, Wei Wu, Yu Wu, Jie Liu, Yalou Huang, Ming Zhou, Wei-Ying Ma","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"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 IJCNN, pages 3506-3513. IEEE, 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":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":26,"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. CoRR, abs/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."}