mlsanityData to 7 Oct 2026

Directed Acyclic Graph Network for Conversational Emotion Recognition

arXiv 2105.12907 ↗First posted 27 May 2021cs.CLcited by 97

Not on the map. Why?

Abstract (arXiv)

The modeling of conversational context plays a vital role in emotion recognition from conversation (ERC). In this paper, we put forward a novel idea of encoding the utterances with a directed acyclic graph (DAG) to better model the intrinsic structure within a conversation, and design a directed acyclic neural network, namely DAG-ERC, to implement this idea. In an attempt to combine the strengths of conventional graph-based neural models and recurrence-based neural models, DAG-ERC provides a more intuitive way to model the information flow between long-distance conversation background and nearby context. Extensive experiments are conducted on four ERC benchmarks with state-of-the-art models employed as baselines for comparison. The empirical results demonstrate the superiority of this new model and confirm the motivation of the directed acyclic graph architecture for ERC.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). Builds on 24 of its 31 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

24 of 31 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2017Graph Attention Networkscited by 8,854
  5. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  6. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  7. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  8. 2018MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversationscited by 636
  9. 2015Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networkscited by 305
  10. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 220
  11. 2018DialogueRNN: An Attentive RNN for Emotion Detection in Conversationscited by 216
  12. 2019DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversationcited by 184
12 more
  1. 2020COSMIC: COmmonSense knowledge for eMotion Identification in Conversationscited by 135
  2. 2019Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advancescited by 118
  3. 2020MIME: MIMicking Emotions for Empathetic Response Generationcited by 114
  4. 2017Emotion Detection on TV Show Transcripts with Sequence-based Convolutional Neural Networkscited by 102
  5. 2019D-VAE: A Variational Autoencoder for Directed Acyclic Graphscited by 98
  6. 2019Knowledge-Enriched Transformer for Emotion Detection in Textual Conversationscited by 92
  7. 2018EmotionLines: An Emotion Corpus of Multi-Party Conversationscited by 80
  8. 2020DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognitioncited by 78
  9. 2021Directed Acyclic Graph Neural Networkscited by 70
  10. 2019HiGRU: Hierarchical Gated Recurrent Units for Utterance-level Emotion Recognitioncited by 43
  11. 2019Improving Graph Neural Network Representations of Logical Formulae with Subgraph Poolingcited by 20
  12. 2015DAG-Recurrent Neural Networks For Scene Labelingcited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 23; 2023: 33; 2024: 21; 2025: 8; 2026: 8.

97 papers.

Sort:

By area:

  1. 2022UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognitioncited by 61
  2. 2023Is ChatGPT Equipped with Emotional Dialogue Capabilities?cited by 54
  3. 2023Towards Interpretable Mental Health Analysis with Large Language Modelscited by 53
  4. 2022EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognitioncited by 48
  5. 2022M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversationcited by 47
  6. 2024MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Modelscited by 41
  7. 2021Contrast and Generation Make BART a Good Dialogue Emotion Recognizercited by 35
  8. 2024Revisiting Multimodal Emotion Recognition in Conversation from the Perspective of Graph Spectrumcited by 33
  9. 2023A Comprehensive Survey on Multi-modal Conversational Emotion Recognition with Deep Learningcited by 32
  10. 2022Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversationcited by 31
  11. 2022COGMEN: COntextualized GNN based Multimodal Emotion recognitioNcited by 29
  12. 2023DialogueLLM: Context and Emotion Knowledge-Tuned Large Language Models for Emotion Recognition in Conversationscited by 29
38 more
  1. 2021Hybrid Curriculum Learning for Emotion Recognition in Conversationcited by 25
  2. 2022Transformers over Directed Acyclic Graphscited by 23
  3. 2022GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognitioncited by 20
  4. 2023Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversationscited by 19
  5. 2023Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interactioncited by 18
  6. 2024Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representationscited by 18
  7. 2023UniSA: Unified Generative Framework for Sentiment Analysiscited by 17
  8. 2021Dyadformer: A Multi-modal Transformer for Long-Range Modeling of Dyadic Interactionscited by 16
  9. 2022Knowledge-Bridged Causal Interaction Network for Causal Emotion Entailmentcited by 16
  10. 2023Cluster-Level Contrastive Learning for Emotion Recognition in Conversationscited by 14
  11. 2023CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognitioncited by 14
  12. 2023Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognitioncited by 14
  13. 2022Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledgecited by 13
  14. 2024LaERC-S: Improving LLM-based Emotion Recognition in Conversation with Speaker Characteristicscited by 13
  15. 2022DialMed: A Dataset for Dialogue-based Medication Recommendationcited by 12
  16. 2022Deep Emotion Recognition in Textual Conversations: A Surveycited by 12
  17. 2024TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversationcited by 12
  18. 2023InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Modelscited by 11
  19. 2024BiosERC: Integrating Biography Speakers Supported by LLMs for ERC Taskscited by 11
  20. 2024LARA: Linguistic-Adaptive Retrieval-Augmentation for Multi-Turn Intent Classificationcited by 10
  21. 2021S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversationcited by 9
  22. 2022DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognitioncited by 9
  23. 2023BERT-ERC: Fine-tuning BERT is Enough for Emotion Recognition in Conversationcited by 9
  24. 2024EmoDynamiX: Emotional Support Dialogue Strategy Prediction by Modelling MiXed Emotions and Discourse Dynamicscited by 9
  25. 2022Speaker-Guided Encoder-Decoder Framework for Emotion Recognition in Conversationcited by 8
  26. 2024Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognitioncited by 8
  27. 2023EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversationcited by 7
  28. 2023Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understandingcited by 7
  29. 2022TSAM: A Two-Stream Attention Model for Causal Emotion Entailmentcited by 6
  30. 2023Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversationcited by 6
  31. 2023Disentangled Variational Autoencoder for Emotion Recognition in Conversationscited by 5
  32. 2022The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversationcited by 4
  33. 2022Contextual Information and Commonsense Based Prompt for Emotion Recognition in Conversationcited by 4
  34. 2022Learning a General Clause-to-Clause Relationships for Enhancing Emotion-Cause Pair Extractioncited by 4
  35. 2022A Review and Roadmap of Deep Learning Causal Discovery in Different Variable Paradigmscited by 4
  36. 2023Mimicking the Thinking Process for Emotion Recognition in Conversation with Prompts and Paraphrasingcited by 4
  37. 2023Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversationscited by 3
  38. 2023How to Enhance Causal Discrimination of Utterances: A Case on Affective Reasoningcited by 3

50 most cited of 97 All 97 (JSON)