ACL Findings2021
Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction
Elsbeth Turcan, Shuai Wang, Rishita Anubhai, Kasturi Bhattacharjee, Yaser Al-Onaizan, Smaranda Muresan
Abstract
Detecting what emotions are expressed in text is a well-studied problem in natural language processing. However, research on finergrained emotion analysis such as what causes an emotion is still in its infancy. We present solutions that tackle both emotion recognition and emotion cause detection in a joint fashion. Considering that common-sense knowledge plays an important role in understanding implicitly expressed emotions and the reasons for those emotions, we propose novel methods that combine common-sense knowledge via adapted knowledge models with multi-task learning to perform joint emotion classification and emotion cause tagging. We show performance improvement on both tasks when including common-sense reasoning and a multitask framework. We provide a thorough analysis to gain insights into model performance.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment cites Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair Extraction
- Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment cites ECPE-2D: Emotion-Cause Pair Extraction based on Joint Two-Dimensional Representation, Interaction and Prediction
- Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailment cites COSMIC: COmmonSense knowledge for eMotion Identification in Conversations
- Uncovering the Causes of Emotions in Software Developer Communication Using Zero-shot LLMs cites GoEmotions: A Dataset of Fine-Grained Emotions
Cited by top-tier papers2
- Knowledge-Bridged Causal Interaction Network for Causal Emotion EntailmentWeixiang Zhao, Yanyan Zhao, Zhuojun Li, Bing QinAAAI 2023 · 48 citations
- Uncovering the Causes of Emotions in Software Developer Communication Using Zero-shot LLMsMia Mohammad Imran, Preetha Chatterjee, Kostadin DamevskiICSE 2024 · 23 citations
Builds on5
- COSMIC: COmmonSense knowledge for eMotion Identification in ConversationsDeepanway Ghosal, Navonil Majumder, Alexander F. Gelbukh, Rada Mihalcea et al.EMNLP Findings 2020 · 390 citations
- ECPE-2D: Emotion-Cause Pair Extraction based on Joint Two-Dimensional Representation, Interaction and PredictionZixiang Ding, Rui Xia, Jianfei YuACL 2020 · 134 citations
- Effective Inter-Clause Modeling for End-to-End Emotion-Cause Pair ExtractionPenghui Wei, Jiahao Zhao, Wenji MaoACL 2020 · 133 citations
- Transition-based Directed Graph Construction for Emotion-Cause Pair ExtractionChuang Fan, Chaofa Yuan, Jiachen Du, Lin Gui et al.ACL 2020 · 110 citations
- GoEmotions: A Dataset of Fine-Grained EmotionsDorottya Demszky, Dana Movshovitz-Attias, Jeongwoo Ko, Alan S. Cowen et al.ACL 2020 · 16 citations
Related papers
- UniMEEC: Towards Unified Multimodal Emotion Recognition and Emotion CauseGuimin Hu, Zhihong Zhu, Daniel Hershcovich, Lijie Hu et al.EMNLP Findings 2024 · 16 citations
- From Coarse to Fine: A Distillation Method for Fine-Grained Emotion-Causal Span Pair Extraction in ConversationXinhao Chen, Chong Yang, Changzhi Sun, Man Lan et al.AAAI 2024 · 7 citations
- Boundary Detection with BERT for Span-level Emotion Cause AnalysisXiangju Li, Wei Gao, Shi Feng, Yifei Zhang et al.ACL Findings 2021 · 26 citations
- Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in ConversationsYunhe Xie, Kailai Yang, Chengjie Sun, Bingquan Liu et al.EMNLP Findings 2021 · 36 citations
- Perspective-taking and Pragmatics for Generating Empathetic Responses Focused on Emotion CausesHyunwoo Kim, Byeongchang Kim, Gunhee KimEMNLP 2021 · 57 citations
