# Dialogue Act Classification with Context-Aware Self-Attention

arXiv: https://arxiv.org/abs/1904.02594 · HTML: https://mlsanity.com/paper/1904.02594/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Apr 2019.

## Built on by (most cited first, 26 of 26)

- [Is ChatGPT Equipped with Emotional Dialogue Capabilities?](https://mlsanity.com/paper/2304.09582/) (2023)
- [Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations](https://mlsanity.com/paper/2111.06647/) (2021)
- [RESPER: Computationally Modelling Resisting Strategies in Persuasive Conversations](https://mlsanity.com/paper/2101.10545/) (2021)
- [Speaker Turn Modeling for Dialogue Act Classification](https://mlsanity.com/paper/2109.05056/) (2021)
- [Modeling Multimodal Social Interactions: New Challenges and Baselines with Densely Aligned Representations](https://mlsanity.com/paper/2403.02090/) (2024)
- [DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition](https://mlsanity.com/paper/2203.03856/) (2022)
- [Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding](https://mlsanity.com/paper/2204.05169/) (2022)
- [Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding](https://mlsanity.com/paper/2306.09114/) (2023)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention](https://mlsanity.com/paper/2305.00262/) (2023)
- [What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition](https://mlsanity.com/paper/2107.02294/) (2021)
- [A Role-Selected Sharing Network for Joint Machine-Human Chatting Handoff and Service Satisfaction Analysis](https://mlsanity.com/paper/2109.08412/) (2021)
- [Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History](https://mlsanity.com/paper/2305.00926/) (2023)
- [BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts](https://mlsanity.com/paper/2512.24885/) (2025)
- [Large-Context Conversational Representation Learning: Self-Supervised Learning for Conversational Documents](https://mlsanity.com/paper/2102.08147/) (2021)
- [Generate, Evaluate, and Select: A Dialogue System with a Response Evaluator for Diversity-Aware Response Generation](https://mlsanity.com/paper/2206.04937/) (2022)
- [Learning functional sections in medical conversations: iterative pseudo-labeling and human-in-the-loop approach](https://mlsanity.com/paper/2210.02658/) (2022)
- [When to generate hedges in peer-tutoring interactions](https://mlsanity.com/paper/2307.15582/) (2023)
- [C-QUERI: Congressional Questions, Exchanges, and Responses in Institutions Dataset](https://mlsanity.com/paper/2509.21548/) (2025)
- [Hierarchical Knowledge Distillation for Dialogue Sequence Labeling](https://mlsanity.com/paper/2111.10957/) (2021)
- [Causal Inference for Chatting Handoff](https://mlsanity.com/paper/2210.02862/) (2022)
- [SSR-TA: Sequence to Sequence based expert recurrent recommendation for ticket automation](https://mlsanity.com/paper/2301.12612/) (2023)
- [InterviewBot: Real-Time End-to-End Dialogue System to Interview Students for College Admission](https://mlsanity.com/paper/2303.15049/) (2023)
- [Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries](https://mlsanity.com/paper/2505.20451/) (2025)
- [From Words to Wisdom: Discourse Annotation and Baseline Models for Student Dialogue Understanding](https://mlsanity.com/paper/2511.20547/) (2025)
- [S-MARC: Causal Streaming Reasoning for Full-Duplex Conversational Behavior Modeling](https://mlsanity.com/paper/2602.11065/) (2026)

## Abstract (arXiv)

Recent work in Dialogue Act classification has treated the task as a sequence labeling problem using hierarchical deep neural networks. We build on this prior work by leveraging the effectiveness of a context-aware self-attention mechanism coupled with a hierarchical recurrent neural network. We conduct extensive evaluations on standard Dialogue Act classification datasets and show significant improvement over state-of-the-art results on the Switchboard Dialogue Act (SwDA) Corpus. We also investigate the impact of different utterance-level representation learning methods and show that our method is effective at capturing utterance-level semantic text representations while maintaining high accuracy.