{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/contrast-and-generation-make-bart-a-good","title":"Contrast and Generation Make BART a Good Dialogue Emotion Recognizer","arxiv_id":"2112.11202","date":"2021-12-21","proceeding":null,"authors":["ShiMin Li","Hang Yan","Xipeng Qiu"],"abstract":"In dialogue systems, utterances with similar semantics may have distinctive emotions under different contexts. Therefore, modeling long-range contextual emotional relationships with speaker dependency plays a crucial part in dialogue emotion recognition. Meanwhile, distinguishing the different emotion categories is non-trivial since they usually have semantically similar sentiments. To this end, we adopt supervised contrastive learning to make different emotions mutually exclusive to identify similar emotions better. Meanwhile, we utilize an auxiliary response generation task to enhance the model's ability of handling context information, thereby forcing the model to recognize emotions with similar semantics in diverse contexts. To achieve these objectives, we use the pre-trained encoder-decoder model BART as our backbone model since it is very suitable for both understanding and generation tasks. The experiments on four datasets demonstrate that our proposed model obtains significantly more favorable results than the state-of-the-art model in dialogue emotion recognition. The ablation study further demonstrates the effectiveness of supervised contrastive loss and generative loss.","url_abs":"https://arxiv.org/abs/2112.11202v2","url_pdf":"https://arxiv.org/pdf/2112.11202v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"contrast-and-generation-make-bart-a-good","repo_url":"https://github.com/whatissimondoing/cog-bart","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"emotion-recognition-in-conversation","task_name":"Emotion Recognition in Conversation"},{"task_slug":"response-generation","task_name":"Response Generation"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bart","method_name":"BART"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"supervised-contrastive-loss","method_name":"Supervised Contrastive Loss"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/emotion-recognition-in-conversation-on-3","task":"Emotion Recognition in Conversation","dataset":"DailyDialog","model":"CoG-BART","rank_in_archive_order":17,"of":22,"metrics":{"Micro-F1":"54.71","Weighted F1":"54.71"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-4","task":"Emotion Recognition in Conversation","dataset":"EmoryNLP","model":"CoG-BART","rank_in_archive_order":13,"of":28,"metrics":{"Micro-F1":"42.58","Weighted-F1":"39.04"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-meld","task":"Emotion Recognition in Conversation","dataset":"MELD","model":"CoG-BART","rank_in_archive_order":37,"of":68,"metrics":{"Weighted-F1":"64.81"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.11202","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}