{"type":"ScholarlyArticle","title":"Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge","authors":[{"name":"Jiangnan Li","slug":"jiangnan-li","given":"Jiangnan","family":"Li","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"},{"name":"Fandong Meng","slug":"fandong-meng","given":"Fandong","family":"Meng","affiliation":"Pattern Recognition Center , WeChat AI , Tencent Inc , China"},{"name":"Zheng Lin","slug":"zheng-lin","given":"Zheng","family":"Lin","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"},{"name":"Rui Liu","slug":"rui-liu","given":"Rui","family":"Liu","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"},{"name":"Peng Fu","slug":"peng-fu","given":"Peng","family":"Fu","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China"},{"name":"Yanan Cao","slug":"yanan-cao","given":"Yanan","family":"Cao","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China; School of Cyber Security , University of Chinese Academy of Sciences , Beijing , China"},{"name":"Weiping Wang","slug":"weiping-wang","given":"Weiping","family":"Wang","affiliation":"Institute of Information Engineering , Chinese Academy of Sciences , Beijing , China"},{"name":"Jie Zhou","slug":"jie-zhou","given":"Jie","family":"Zhou","affiliation":"Pattern Recognition Center , WeChat AI , Tencent Inc , China"}],"abstract":"Conversational Causal Emotion Entailment aims to detect causal utterances for a non-neutral targeted utterance from a conversation. In this work, we build conversations as graphs to overcome implicit contextual modelling of the original entailment style. Following the previous work, we further introduce the emotion information into graphs. Emotion information can markedly promote the detection of causal utterances whose emotion is the same as the targeted utterance. However, it is still hard to detect causal utterances with different emotions, especially neutral ones. The reason is that models are limited in reasoning causal clues and passing them between utterances. To alleviate this problem, we introduce social commonsense knowledge (CSK) and propose a Knowledge Enhanced Conversation graph (KEC). KEC propagates the CSK between two utterances. As not all CSK is emotionally suitable for utterances, we therefore propose a sentiment-realized knowledge selecting strategy to filter CSK. To process KEC, we further construct the Knowledge Enhanced Directed Acyclic Graph networks. Experimental results show that our method outperforms baselines and infers more causes with different emotions from the targeted utterance.","doi":"10.24963/ijcai.2022/584","url":"https://ijcai.org/proceedings/2022/584","pdf":"https://ijcai.org/proceedings/2022/0584.pdf","markdown":"https://ijcai.org/proceedings/2022/584.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/584","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":584,"pages":{"first":4209,"last":4215},"keywords":["Natural Language Processing: Text Classification","Natural Language Processing: Sentiment Analysis and Text Mining"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987026","length_sec":86,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985169","length_sec":691,"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, pages 4762- 4779, 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":"[Ding et al., 2019] Zixiang Ding, Huihui He, Mengran Zhang, and Rui Xia. From independent prediction to re- ordered prediction: Integrating relative position and global label information to emotion cause identification. In AAAI, pages 6343-6350, 2019.","title":"From independent prediction to reordered prediction: Integrating relative position and global label information to emotion cause identification","authors":"Ding","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Ding et al., 2020a] Zixiang Ding, Rui Xia, and Jianfei Yu. ECPE-2D: emotion-cause pair extraction based on joint two-dimensional representation, interaction and predic- tion. In ACL, pages 3161-3170, 2020.","title":"ECPE-2D: emotion-cause pair extraction based on joint two-dimensional representation, interaction and prediction","authors":"Ding","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ding et al., 2020b] Zixiang Ding, Rui Xia, and Jianfei Yu. End-to-end emotion-cause pair extraction based on slid- ing window multi-label learning. In EMNLP, pages 3574- 3583, 2020.","title":"End-to-end emotion-cause pair extraction based on sliding window multi-label learning","authors":"Ding","year":"2020","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ghosal et al., 2019] Deepanway Ghosal, Navonil Ma- jumder, Soujanya Poria, Niyati Chhaya, and Alexander F. Gelbukh. Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation. In EMNLP-IJCNLP, pages 154-164, 2019.","title":"Dialoguegcn: A graph convolutional neural network for emotion recognition in conversation","authors":"Ghosal","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ghosal et al., 2020] Deepanway Ghosal, Navonil Ma- jumder, Alexander F. Gelbukh, Rada Mihalcea, and Soujanya Poria. COSMIC: commonsense knowledge for emotion identification in conversations. In Findings of EMNLP, pages 2470-2481, 2020.","title":"COSMIC: commonsense knowledge for emotion identification in conversations","authors":"Ghosal","year":"2020","venue":"Findings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ghosal et al., 2021] Deepanway Ghosal, Navonil Ma- jumder, Rada Mihalcea, and Soujanya Poria. Stack: Sentence ordering with temporal commonsense knowl- edge. In EMNLP, pages 8676-8686, 2021.","title":"Stack: Sentence ordering with temporal commonsense knowledge","authors":"Ghosal","year":"2021","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Gui et al., 2016] Lin Gui, Ruifeng Xu, Qin Lu, Dongyin Wu, and Yu Zhou. Emotion cause extraction, A challeng- ing task with corpus construction. In SMP, 2016.","title":"Emotion cause extraction, A challenging task with corpus construction","authors":"Lin Gui, Ruifeng Xu, Qin Lu, Dongyin Wu, Yu Zhou","year":"2016","venue":"SMP","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hwang et al., 2021] Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, and Yejin Choi. (comet-) atomic 2020: On symbolic and neural commonsense knowledge graphs. In AAAI, pages 6384-6392, 2021.","title":"comet-) atomic 2020: On symbolic and neural commonsense knowledge graphs","authors":"Jena D Hwang, Chandra Bhagavatula, Le Ronan, Jeff Bras, Keisuke Da, Antoine Sakaguchi, Yejin Bosselut, Choi","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kim et al., 2021] Hyunwoo Kim, Byeongchang Kim, and Gunhee Kim. Perspective-taking and pragmatics for gen- erating empathetic responses focused on emotion causes. In EMNLP, pages 2227-2240, 2021.","title":"Perspective-taking and pragmatics for generating empathetic responses focused on emotion causes","authors":"Hyunwoo Kim, Byeongchang Kim, Gunhee Kim","year":"2021","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Li et al., 2017] Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. Dailydialog: A manually labelled multi-turn dialogue dataset. In IJCNLP, 2017.","title":"Dailydialog: A manually labelled multi-turn dialogue dataset","authors":"Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, Shuzi Niu","year":"2017","venue":"IJCNLP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Li et al., 2021] Jiangnan Li, Zheng Lin, Peng Fu, and Weip- ing Wang. Past, present, and future: Conversational emo- tion recognition through structural modeling of psycholog- ical knowledge. In Findings of EMNLP, 2021.","title":"Past, present, and future: Conversational emotion recognition through structural modeling of psychological knowledge","authors":"Li","year":"2021","venue":"Findings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Liang et al., 2021] Yunlong Liang, Fandong Meng, Ying Zhang, Yufeng Chen, Jinan Xu, and Jie Zhou. Infusing multi-source knowledge with heterogeneous graph neural network for emotional conversation generation. In AAAI, pages 8676-8686, 2021.","title":"Infusing multi-source knowledge with heterogeneous graph neural network for emotional conversation generation","authors":"Yunlong Liang, Fandong Meng, Ying Zhang, Yufeng Chen, Jinan Xu, Jie Zhou","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2019] Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. Roberta: A robustly optimized BERT pretraining approach. CoRR, abs/1907.11692, 2019.","title":"Roberta: A robustly optimized BERT pretraining approach","authors":"Liu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Majumder et al., 2019] Navonil Majumder, Soujanya Poria, Devamanyu Hazarika, Rada Mihalcea, Alexander F. Gel- bukh, and Erik Cambria. Dialoguernn: An attentive RNN for emotion detection in conversations. In AAAI, 2019.","title":"Dialoguernn: An attentive RNN for emotion detection in conversations","authors":"Majumder","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Poria et al., 2021] Soujanya Poria, Navonil Majumder, De- vamanyu Hazarika, Deepanway Ghosal, Rishabh Bhard- waj, Samson Yu Bai Jian, Pengfei Hong, Romila Ghosh, Abhinaba Roy, Niyati Chhaya, Alexander F. Gelbukh, and Rada Mihalcea. Recognizing emotion cause in conversa- tions. Cogn. Comput., 13(5):1317-1332, 2021.","title":"Recognizing emotion cause in conversations","authors":"Poria","year":"2021","venue":"Cogn. Comput","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Shen et al., 2021a] Weizhou Shen, Junqing Chen, Xiaojun Quan, and Zhixian Xie. Dialogxl: All-in-one xlnet for multi-party conversation emotion recognition. In AAAI, 2021.","title":"Dialogxl: All-in-one xlnet for multi-party conversation emotion recognition","authors":"Shen","year":"2021","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Shen et al., 2021b] Weizhou Shen, Siyue Wu, Yunyi Yang, and Xiaojun Quan. Directed acyclic graph network for conversational emotion recognition. In ACL/IJCNLP, pages 1551-1560, 2021.","title":"Directed acyclic graph network for conversational emotion recognition","authors":"Shen","year":"2021","venue":"ACL/IJCNLP","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shi et al., 2021] Yunsheng Shi, Zhengjie Huang, Shikun Feng, Hui Zhong, Wenjing Wang, and Yu Sun. Masked label prediction: Unified message passing model for semi- supervised classification. In IJCAI, 2021.","title":"Masked label prediction: Unified message passing model for semisupervised classification","authors":"Yunsheng Shi, Zhengjie Huang, Shikun Feng, Hui Zhong, Wenjing Wang, Yu Sun","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Turcan et al., 2021] Elsbeth Turcan, Shuai Wang, Rishita Anubhai, Kasturi Bhattacharjee, Yaser Al-Onaizan, and Smaranda Muresan. Multi-task learning and adapted knowledge models for emotion-cause extraction. In ACL/IJCNLP, pages 3975-3989, 2021.","title":"Multi-task learning and adapted knowledge models for emotion-cause extraction","authors":"Elsbeth Turcan, Shuai Wang, Rishita Anubhai, Kasturi Bhattacharjee, Yaser Al-Onaizan, Smaranda Muresan","year":"2021","venue":"ACL/IJCNLP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wei et al., 2020] Penghui Wei, Jiahao Zhao, and Wenji Mao. Effective inter-clause modeling for end-to-end emotion-cause pair extraction. In ACL, 2020.","title":"Effective inter-clause modeling for end-to-end emotion-cause pair extraction","authors":"Wei","year":"2020","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Xia and Ding, 2019] Rui Xia and Zixiang Ding. Emotion- cause pair extraction: A new task to emotion analysis in texts. In ACL, pages 1003-1012, 2019.","title":"Emotioncause pair extraction: A new task to emotion analysis in texts","authors":"Rui Xia, Zixiang Ding","year":"2019","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Xia et al., 2019] Rui Xia, Mengran Zhang, and Zixiang Ding. RTHN: A rnn-transformer hierarchical network for emotion cause extraction. In IJCAI, 2019.","title":"RTHN: A rnn-transformer hierarchical network for emotion cause extraction","authors":"Rui Xia, Mengran Zhang, Zixiang Ding","year":"2019","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2019/734"},{"position":24,"raw":"[Yan et al., 2021] Hanqi Yan, Lin Gui, Gabriele Pergola, and Yulan He. Position bias mitigation: A knowledge- aware graph model for emotion cause extraction. In ACL/IJCNLP, pages 3364-3375, 2021.","title":"Position bias mitigation: A knowledgeaware graph model for emotion cause extraction","authors":"Yan","year":"2021","venue":"ACL/IJCNLP","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhong et al., 2019] Peixiang Zhong, Di Wang, and Chun- yan Miao. Knowledge-enriched transformer for emotion detection in textual conversations. In EMNLP-IJCNLP, pages 165-176, 2019.","title":"Knowledge-enriched transformer for emotion detection in textual conversations","authors":"Peixiang Zhong, Di Wang, Chunyan Miao","year":"2019","venue":"EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}