EMNLP Findings2023
Task-Aware Self-Supervised Framework for Dialogue Discourse Parsing
Wei Li, Luyao Zhu, Wei Shao, Zonglin Yang, Erik Cambria
Abstract
Dialogue discourse parsing is a fundamental natural language processing task. It can benefit a series of conversation-related downstream tasks including dialogue summarization and emotion recognition in conversations. However, existing parsing approaches are constrained by predefined relation types, which can impede the adaptability of the parser for downstream tasks. To this end, we propose to introduce a taskaware paradigm to improve the versatility of the parser in this paper. Moreover, to alleviate error propagation and learning bias, we design a graph-based discourse parsing model termed DialogDP. Building upon the symmetrical property of matrix-embedded parsing graphs, we have developed an innovative self-supervised mechanism that leverages both bottom-up and top-down parsing strategies. This approach allows the parsing graphs to mutually regularize and enhance each other. Empirical studies on dialogue discourse parsing datasets and a downstream task demonstrate the effectiveness and flexibility of our framework 1 .
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.
Lineage
Builds on5
- Graph Transformer for Graph-to-Sequence LearningDeng Cai, Wai LamAAAI 2020 · 247 citations
- Efficient Second-Order TreeCRF for Neural Dependency ParsingYu Zhang, Zhenghua Li, Min ZhangACL 2020 · 90 citations
- SKIER: A Symbolic Knowledge Integrated Model for Conversational Emotion RecognitionWei Li, Luyao Zhu, Rui Mao, Erik CambriaAAAI 2023 · 85 citations
- A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational SpeechJingxuan Yang, Kerui Xu, Jun Xu, Si Li et al.ACL 2021
- Structural Pre-training for Dialogue ComprehensionZhuosheng Zhang, Hai ZhaoACL 2021
Related papers
- Improving Dialogue Discourse Parsing via Reply-to Structures of Addressee RecognitionYaxin Fan, Feng Jiang, Peifeng Li, Fang Kong et al.EMNLP 2023 · 4 citations
- Improving Dialogue Discourse Parsing through Discourse-aware Utterance ClarificationYaxin Fan, Peifeng Li, Qiaoming ZhuACL 2025
- CoMuMDR: Code-mixed Multi-modal Multi-domain corpus for Discourse paRsing in conversationsDivyaksh Shukla, Ritesh Baviskar, Dwijesh Gohil, Aniket Tiwari et al.ACL Findings 2025 · 1 citation
- GraphDialog: Integrating Graph Knowledge into End-to-End Task-Oriented Dialogue SystemsShiquan Yang, Rui Zhang, Sarah M. ErfaniEMNLP 2020 · 46 citations
- WebDP: Understanding Discourse Structures in Semi-Structured Web DocumentsPeilin Liu, Hongyu Lin, Meng Liao, Hao Xiang et al.ACL Findings 2023
