# Speaker Turn Modeling for Dialogue Act Classification

arXiv: https://arxiv.org/abs/2109.05056 · HTML: https://mlsanity.com/paper/2109.05056/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 30 references that are in the map.
- First posted on arXiv 10 Sep 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset](https://mlsanity.com/paper/1710.03957/) (2017)
- [Adversarial Learning for Neural Dialogue Generation](https://mlsanity.com/paper/1701.06547/) (2017)
- [Co-GAT: A Co-Interactive Graph Attention Network for Joint Dialog Act Recognition and Sentiment Classification](https://mlsanity.com/paper/2012.13260/) (2020)
- [Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks](https://mlsanity.com/paper/1603.03827/) (2016)
- [Dialogue Act Classification with Context-Aware Self-Attention](https://mlsanity.com/paper/1904.02594/) (2019)
- [Guiding attention in Sequence-to-sequence models for Dialogue Act prediction](https://mlsanity.com/paper/2002.08801/) (2020)
- [Dialogue Act Recognition via CRF-Attentive Structured Network](https://mlsanity.com/paper/1711.05568/) (2017)
- [Dialogue Act Sequence Labeling using Hierarchical encoder with CRF](https://mlsanity.com/paper/1709.04250/) (2017)
- [A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification](https://mlsanity.com/paper/1810.09154/) (2018)
- [Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning](https://mlsanity.com/paper/1710.00164/) (2017)
- [A Latent Variable Recurrent Neural Network for Discourse Relation Language Models](https://mlsanity.com/paper/1603.01913/) (2016)
- [A Context-based Approach for Dialogue Act Recognition using Simple Recurrent Neural Networks](https://mlsanity.com/paper/1805.06280/) (2018)
- [Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding](https://mlsanity.com/paper/1710.00165/) (2017)

## Built on by (most cited first, 18 of 18)

- [Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding](https://mlsanity.com/paper/2210.14169/) (2022)
- [Capturing Perspectives of Crowdsourced Annotators in Subjective Learning Tasks](https://mlsanity.com/paper/2311.09743/) (2023)
- [Multi-Party Conversational Agents: A Survey](https://mlsanity.com/paper/2505.18845/) (2025)
- [TheraMind: A Strategic and Adaptive Agent for Longitudinal Psychological Counseling](https://mlsanity.com/paper/2510.25758/) (2025)
- [Revisiting Conversation Discourse for Dialogue Disentanglement](https://mlsanity.com/paper/2306.03975/) (2023)
- [Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling](https://mlsanity.com/paper/2312.03523/) (2023)
- [A Speaker Turn-Aware Multi-Task Adversarial Network for Joint User Satisfaction Estimation and Sentiment Analysis](https://mlsanity.com/paper/2410.09556/) (2024)
- [Towards Actionable Pedagogical Feedback: A Multi-Perspective Analysis of Mathematics Teaching and Tutoring Dialogue](https://mlsanity.com/paper/2505.07161/) (2025)
- [BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts](https://mlsanity.com/paper/2512.24885/) (2025)
- [Pragmatically Appropriate Diversity for Dialogue Evaluation](https://mlsanity.com/paper/2304.02812/) (2023)
- [Reducing Sensitivity on Speaker Names for Text Generation from Dialogues](https://mlsanity.com/paper/2305.13833/) (2023)
- [Intention and Face in Dialog](https://mlsanity.com/paper/2406.04109/) (2024)
- [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)
- [LiFT: How to Enable In-Context Learning for Longitudinal Modelling](https://mlsanity.com/paper/2604.16382/) (2026)
- [Leveraging Turn-taking Dynamics for Intent Recognition in Multi-party Conversations](https://mlsanity.com/paper/2608.28926/) (2026)
- [Understanding Clinical Cognitive Dialogues Using Large Language Models](https://mlsanity.com/paper/2609.34125/) (2026)

## Abstract (arXiv)

Dialogue Act (DA) classification is the task of classifying utterances with respect to the function they serve in a dialogue. Existing approaches to DA classification model utterances without incorporating the turn changes among speakers throughout the dialogue, therefore treating it no different than non-interactive written text. In this paper, we propose to integrate the turn changes in conversations among speakers when modeling DAs. Specifically, we learn conversation-invariant speaker turn embeddings to represent the speaker turns in a conversation; the learned speaker turn embeddings are then merged with the utterance embeddings for the downstream task of DA classification. With this simple yet effective mechanism, our model is able to capture the semantics from the dialogue content while accounting for different speaker turns in a conversation. Validation on three benchmark public datasets demonstrates superior performance of our model.