ACL Findings2022
DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition
Bowen Xing, Ivor W. Tsang
Abstract
The task of joint dialog sentiment classification (DSC) and act recognition (DAR) aims to simultaneously predict the sentiment label and act label for each utterance in a dialog. In this paper, we put forward a new framework which models the explicit dependencies via integrating prediction-level interactions other than semantics-level interactions, more consistent with human intuition. Besides, we propose a speaker-aware temporal graph (SATG) and a dual-task relational temporal graph (DRTG) to introduce temporal relations into dialog understanding and dual-task reasoning. To implement our framework, we propose a novel model dubbed DARER, which first generates the context-, speaker-and temporal-sensitive utterance representations via modeling SATG, then conducts recurrent dual-task relational reasoning on DRTG, in which process the estimated label distributions act as key clues in prediction-level interactions. Experiment results show that DARER outperforms existing models by large margins while requiring much less computation resource and costing less training time. Remarkably, on DSC task in Mastodon, DARER gains a relative improvement of about 25% over previous best model in terms of F1, with less than 50% parameters and about only 60% required GPU memory.
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
- Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification cites DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification
- Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study cites Towards Emotion-aided Multi-modal Dialogue Act Classification
- Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical Study cites DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification
Cited by top-tier papers2
- Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label GraphsBowen Xing, Ivor W. TsangEMNLP 2022 · 36 citations
- Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot FillingBowen Xing, Ivor W. TsangEMNLP 2022 · 24 citations
Builds on7
- Real-Time Emotion Recognition via Attention Gated Hierarchical Memory NetworkWenxiang Jiao, Michael R. Lyu, Irwin KingAAAI 2020 · 149 citations
- DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment ClassificationLibo Qin, Wanxiang Che, Yangming Li, Minheng Ni et al.AAAI 2020 · 100 citations
- Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment ClassificationLibo Qin, Zhouyang Li, Wanxiang Che, Minheng Ni et al.AAAI 2021 · 77 citations
- Towards Emotion-aided Multi-modal Dialogue Act ClassificationTulika Saha, Aditya Prakash Patra, Sriparna Saha, Pushpak BhattacharyyaACL 2020 · 63 citations
- Exploring the Role of Context in Utterance-level Emotion, Act and Intent Classification in Conversations: An Empirical StudyDeepanway Ghosal, Navonil Majumder, Rada Mihalcea, Soujanya PoriaACL Findings 2021 · 17 citations
Related papers
- DualGATs: Dual Graph Attention Networks for Emotion Recognition in ConversationsDuzhen Zhang, Feilong Chen, Xiuyi ChenACL 2023 · 54 citations
- DMIN: A Discourse-specific Multi-granularity Integration Network for Conversational Aspect-based Sentiment Quadruple AnalysisPeijie Huang, Xisheng Xiao, Yuhong Xu, Jiawei ChenACL Findings 2024 · 12 citations
- Harnessing Holistic Discourse Features and Triadic Interaction for Sentiment Quadruple Extraction in DialoguesBobo Li, Hao Fei, Lizi Liao, Yu Zhao et al.AAAI 2024 · 22 citations
- A Speaker Turn-Aware Multi-Task Adversarial Network for Joint User Satisfaction Estimation and Sentiment AnalysisKaisong Song, Yangyang Kang, Jiawei Liu, Xurui Li et al.AAAI 2023 · 5 citations
- Span-Pair Interaction and Tagging for Dialogue-Level Aspect-Based Sentiment Quadruple AnalysisChangzhi Zhou, Zhijing Wu, Dandan Song, Linmei Hu et al.WWW 2024 · 8 citations
