{"type":"ScholarlyArticle","title":"Control Globally, Understand Locally: A Global-to-Local Hierarchical Graph Network for Emotional Support Conversation","authors":[{"name":"Wei Peng","slug":"wei-peng","given":"Wei","family":"Peng","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , China; School of Cyber Security , University of Chinese Academy of Sciences , China"},{"name":"Yue Hu","slug":"yue-hu","given":"Yue","family":"Hu","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , China; School of Cyber Security , University of Chinese Academy of Sciences , China"},{"name":"Luxi Xing","slug":"luxi-xing","given":"Luxi","family":"Xing","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , China; School of Cyber Security , University of Chinese Academy of Sciences , China"},{"name":"Yuqiang Xie","slug":"yuqiang-xie","given":"Yuqiang","family":"Xie","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , China; School of Cyber Security , University of Chinese Academy of Sciences , China"},{"name":"Yajing Sun","slug":"yajing-sun","given":"Yajing","family":"Sun","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , China; School of Cyber Security , University of Chinese Academy of Sciences , China"},{"name":"Yunpeng Li","slug":"yunpeng-li","given":"Yunpeng","family":"Li","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , China; School of Cyber Security , University of Chinese Academy of Sciences , China"}],"abstract":"Emotional support conversation aims at reducing the emotional distress of the help-seeker, which is a new and challenging task. It requires the system to explore the cause of help-seeker's emotional distress and understand their psychological intention to provide supportive responses. However, existing methods mainly focus on the sequential contextual information, ignoring the hierarchical relationships with the global cause and local psychological intention behind conversations, thus leads to a weak ability of emotional support. In this paper, we propose a Global-to-Local Hierarchical Graph Network to capture the multi-source information (global cause, local intentions and dialog history) and model hierarchical relationships between them, which consists of a multi-source encoder, a hierarchical graph reasoner, and a global-guide decoder. Furthermore, a novel training objective is designed to monitor semantic information of the global cause. Experimental results on the emotional support conversation dataset, ESConv, confirm that the proposed GLHG has achieved the state-of-the-art performance on the automatic and human evaluations.","doi":"10.24963/ijcai.2022/600","url":"https://ijcai.org/proceedings/2022/600","pdf":"https://ijcai.org/proceedings/2022/0600.pdf","markdown":"https://ijcai.org/proceedings/2022/600.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/600","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Natural Language Processing","track":"Main Track","number":600,"pages":{"first":4324,"last":4330},"keywords":["Natural Language Processing: Language Generation","Natural Language Processing: Dialogue and Interactive Systems"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986688","length_sec":80,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984831","length_sec":325,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Bosselut et al., 2019] Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. COMET: commonsense transformers for auto- matic knowledge graph construction. In ACL, 2019.","title":"COMET: commonsense transformers for automatic knowledge graph construction","authors":"Bosselut","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Burleson et al., 2006] Brant R. Burleson, Steven T. Morten- son, and et al. Chinese evaluations of emotional support skills, goals, and behaviors. Commun. Res., 2006.","title":"Chinese evaluations of emotional support skills, goals, and behaviors","authors":"R Brant, Steven T Burleson, Mortenson","year":"2006","venue":"Commun. Res","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ghosal et al., 2019] Deepanway Ghosal, Navonil Majumder, Alexander F. Gelbukh, and et al. Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. In EMNLP, 2019.","title":"Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation","authors":"Ghosal","year":"2019","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Guo et al., 2021] Lei Guo, Li Tang, Hongzhi Yin, and et al. DA-GCN: A domain-aware attentive graph convolution network for shared-account cross-domain sequential rec- ommendation. In IJCAI, 2021.","title":"DA-GCN: A domain-aware attentive graph convolution network for shared-account cross-domain sequential recommendation","authors":"Lei Guo, Li Tang, Hongzhi Yin","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/342"},{"position":5,"raw":"[Heaney and Israel, 2008] Catherine A Heaney and Bar- bara A Israel. Social networks and social support. Health behavior and health education: Theory, research, and prac- tice, 4:189-210, 2008.","title":"Social networks and social support","authors":"Catherine","year":"2008","venue":"Health behavior and health education: Theory, research, and practice","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Huang et al., 2020] Minlie Huang, Xiaoyan Zhu, and Jian- feng Gao. Challenges in building intelligent open-domain dialog systems. ACM Trans. Inf. Syst., 2020.","title":"Challenges in building intelligent open-domain dialog systems","authors":"Huang","year":"2020","venue":"ACM Trans. Inf. Syst","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Li et al., 2016] Jiwei Li, Michel Galley, Chris Brockett, Jian- feng Gao, and Bill Dolan. A diversity-promoting objective function for neural conversation models. In ACL, 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":"ACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Lin et al., 2019] Zhaojiang Lin, Andrea Madotto, Jamin Shin, Peng Xu, and Pascale Fung. Moel: Mixture of empa- thetic listeners. In EMNLP-IJCNLP, 2019.","title":"Moel: Mixture of empathetic listeners","authors":"Lin","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Liu et al., 2021] Siyang Liu, Chujie Zheng, Orianna Demasi, Zhou Yu, Yong Jiang, Minlie Huang, and et al. Towards emotional support dialog systems. In ACL/IJCNLP, 2021.","title":"Towards emotional support dialog systems","authors":"Siyang Liu, Chujie Zheng, Orianna Demasi, Zhou Yu, Yong Jiang, Minlie Huang","year":"2021","venue":"ACL/IJCNLP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Loshchilov and Hutter, 2017] Ilya Loshchilov and Frank Hutter. Fixing weight decay regularization in adam. ArXiv, abs/1711.05101, 2017.","title":"Ilya Loshchilov and Frank Hutter. Fixing weight decay regularization in adam","authors":"Hutter Loshchilov","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Majumder et al., 2020] Navonil Majumder, Pengfei Hong, Soujanya Poria, and et al. MIME: mimicking emotions for empathetic response generation. In Proc. of EMNLP, 2020.","title":"MIME: mimicking emotions for empathetic response generation","authors":"Majumder","year":"2020","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Peng et al., 2021] Wei Peng, Yue Hu, and et al. APER: adap- tive evidence-driven reasoning network for machine read- ing comprehension with unanswerable questions. Knowl. Based Syst., 229:107364, 2021.","title":"APER: adaptive evidence-driven reasoning network for machine reading comprehension with unanswerable questions","authors":"Wei Peng, Yue Hu","year":"2021","venue":"Knowl. Based Syst","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Peng et al., 2022] Wei Peng, Yue Hu, and et al. Modeling intention, emotion and external world in dialogue systems. CoRR, abs/2202.06476, 2022.","title":"Modeling intention, emotion and external world in dialogue systems","authors":"Wei Peng, Yue Hu","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Qin et al., 2021] Libo Qin, Zhouyang Li, Wanxiang Che, Minheng Ni, and Ting Liu. Co-gat: A co-interactive graph attention network for joint dialog act recognition and senti- ment classification. In Proc. of AAAI, 2021.","title":"Co-gat: A co-interactive graph attention network for joint dialog act recognition and sentiment classification","authors":"Libo Qin, Zhouyang Li, Wanxiang Che, Minheng Ni, Ting Liu","year":"2021","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Rains et al., 2020] Stephen A. Rains, Anjali Ashtaputre, and et al. Support seeker expectations, support message quality, and supportive interaction processes and outcomes: The case of the comforting computer program revisited. Journal of Social and Personal Relationships, 2020. [","title":"Support seeker expectations, support message quality, and supportive interaction processes and outcomes: The case of the comforting computer program revisited","authors":"Stephen A Rains, Anjali Ashtaputre","year":"2020","venue":"Journal of Social and Personal Relationships","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Rashkin et al., 2019] Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. Towards empathetic open-domain conversation models: A new benchmark and dataset. In Proc. of ACL, 2019.","title":"Towards empathetic open-domain conversation models: A new benchmark and dataset","authors":"Rashkin","year":"2019","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Roller et al., 2021] Stephen Roller, Emily Dinan, Naman Goyal, Y.-Lan Boureau, Jason Weston, and et al. Recipes for building an open-domain chatbot. In EACL, 2021.","title":"Recipes for building an open-domain chatbot","authors":"Stephen Roller, Emily Dinan, Naman Goyal, Y.-Lan Boureau, Jason Weston","year":"2021","venue":"EACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sap et al., 2019] Maarten Sap, Ronan Le Bras, Emily All- away, Noah A. Smith, Yejin Choi, and et al. ATOMIC: an atlas of machine commonsense for if-then reasoning. In Proc. of AAAI, 2019.","title":"ATOMIC: an atlas of machine commonsense for if-then reasoning","authors":"Sap","year":"2019","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Scarselli et al., 2009] Franco Scarselli, Ah Chung Tsoi, and Gabriele Monfardini. The graph neural network model. IEEE Trans. Neural Networks, 2009.","title":"The graph neural network model","authors":"Franco Scarselli, Ah Chung Tsoi, Gabriele Monfardini","year":"2009","venue":"IEEE Trans. Neural Networks","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Slovák et al., 2015] Petr Slovák, Ran Gilad-Bachrach, and Geraldine Fitzpatrick. Designing social and emotional skills training: The challenges and opportunities for tech- nology support. In CHI, 2015.","title":"Designing social and emotional skills training: The challenges and opportunities for technology support","authors":"Slovák","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sun et al., 2021] Yajing Sun, Chengguang Tang, and et al. Unsupervised learning of deterministic dialogue structure with edge-enhanced graph auto-encoder. In AAAI, 2021.","title":"Yajing Sun, Chengguang Tang, and et al. Unsupervised learning of deterministic dialogue structure with edge-enhanced graph auto-encoder","authors":"Sun","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[van der Zwaan et al., 2012] Janneke M. van der Zwaan, Vir- ginia Dignum, and Catholijn M. Jonker. A bdi dialogue agent for social support: Specification and evaluation method. In AAMAS, 2012.","title":"A bdi dialogue agent for social support: Specification and evaluation method","authors":"M Janneke, Virginia Van Der Zwaan, Catholijn M Dignum, Jonker","year":"2012","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Lukasz Kaiser, Illia Polosukhin, and et al. Attention is all you need. In NIPS, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Velickovic et al., 2017] Petar Velickovic, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. Graph attention networks. CoRR, 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":25,"raw":"[Xing et al., 2020] Luxi Xing, Wei Peng, and et al. IIE- NLP-NUT at semeval-2020 task 4: Guiding PLM with prompt template reconstruction strategy for comve. In SemEval@COLING, 2020.","title":"IIE-NLP-NUT at semeval-2020 task 4: Guiding PLM with prompt template reconstruction strategy for comve","authors":"Luxi Xing, Wei Peng","year":"2020","venue":"SemEval@COLING","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Xu et al., 2021] Jun Xu, Zeyang Lei, Hua Wu, Wanxiang Che, and et al. Discovering dialog structure graph for coherent dialog generation. In ACL, 2021.","title":"Discovering dialog structure graph for coherent dialog generation","authors":"Jun Xu, Zeyang Lei, Hua Wu, Wanxiang Che","year":"2021","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yu et al., 2020] Wenhao Yu, Meng Jiang, and et al. A survey of knowledge-enhanced text generation. CoRR, abs/2010.04389, 2020.","title":"A survey of knowledge-enhanced text generation","authors":"Wenhao Yu, Meng Jiang","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Zhang et al., 2020] Yizhe Zhang, Siqi Sun, Michel Galley, Jingjing Liu, William B. Dolan, and et al. Dialogpt : Large- scale generative pre-training for conversational response generation. In ACL, 2020.","title":"Dialogpt : Largescale generative pre-training for conversational response generation","authors":"Zhang","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zhou et al., 2018] Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, and Bing Liu. Emotional chatting machine: Emotional conversation generation with internal and external memory. In Proc. of AAAI, 2018.","title":"Emotional chatting machine: Emotional conversation generation with internal and external memory","authors":"Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, Bing Liu","year":"2018","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhou et al., 2020] Li Zhou, Jianfeng Gao, Di Li, and Heung- Yeung Shum. The design and implementation of xiaoice, an empathetic social chatbot. Comput. Linguistics, 2020.","title":"The design and implementation of xiaoice, an empathetic social chatbot","authors":"Li Zhou, Jianfeng Gao, Di Li, Heung-Yeung Shum","year":"2020","venue":"Comput. Linguistics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}