# Guiding attention in Sequence-to-sequence models for Dialogue Act prediction

arXiv: https://arxiv.org/abs/2002.08801 · HTML: https://mlsanity.com/paper/2002.08801/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Feb 2020.

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

- [Of Human Criteria and Automatic Metrics: A Benchmark of the Evaluation of Story Generation](https://mlsanity.com/paper/2208.11646/) (2022)
- [Automatic Text Evaluation through the Lens of Wasserstein Barycenters](https://mlsanity.com/paper/2108.12463/) (2021)
- [A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations](https://mlsanity.com/paper/2105.02685/) (2021)
- [InfoLM: A New Metric to Evaluate Summarization & Data2Text Generation](https://mlsanity.com/paper/2112.01589/) (2021)
- [Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations](https://mlsanity.com/paper/2111.06647/) (2021)
- [Speaker Turn Modeling for Dialogue Act Classification](https://mlsanity.com/paper/2109.05056/) (2021)
- [Self-seeding and Multi-intent Self-instructing LLMs for Generating Intent-aware Information-Seeking dialogs](https://mlsanity.com/paper/2402.11633/) (2024)
- [A Pseudo-Metric between Probability Distributions based on Depth-Trimmed Regions](https://mlsanity.com/paper/2103.12711/) (2021)
- [Unsupervised Layer-wise Score Aggregation for Textual OOD Detection](https://mlsanity.com/paper/2302.09852/) (2023)
- [Learning Disentangled Textual Representations via Statistical Measures of Similarity](https://mlsanity.com/paper/2205.03589/) (2022)
- [Towards More Robust NLP System Evaluation: Handling Missing Scores in Benchmarks](https://mlsanity.com/paper/2305.10284/) (2023)
- [Code-switched inspired losses for generic spoken dialog representations](https://mlsanity.com/paper/2108.12465/) (2021)
- [The Glass Ceiling of Automatic Evaluation in Natural Language Generation](https://mlsanity.com/paper/2208.14585/) (2022)
- [Towards End-to-End Integration of Dialog History for Improved Spoken Language Understanding](https://mlsanity.com/paper/2204.05169/) (2022)
- [What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition](https://mlsanity.com/paper/2107.02294/) (2021)
- [Modeling Intention, Emotion and External World in Dialogue Systems](https://mlsanity.com/paper/2202.06476/) (2022)
- [Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog History](https://mlsanity.com/paper/2305.00926/) (2023)
- [Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations](https://mlsanity.com/paper/2411.00128/) (2024)
- [CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspective](https://mlsanity.com/paper/2205.03540/) (2022)
- [Unifying Token and Span Level Supervisions for Few-Shot Sequence Labeling](https://mlsanity.com/paper/2307.07946/) (2023)
- [A Novel Information-Theoretic Objective to Disentangle Representations for Fair Classification](https://mlsanity.com/paper/2310.13990/) (2023)
- [Synthetic Audio Helps for Cognitive State Tasks](https://mlsanity.com/paper/2502.06922/) (2025)
- [Switchboard-Affect: Emotion Perception Labels from Conversational Speech](https://mlsanity.com/paper/2510.13906/) (2025)
- [Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations](https://mlsanity.com/paper/2604.18539/) (2026)
- [A survey of neural models for the automatic analysis of conversation: Towards a better integration of the social sciences](https://mlsanity.com/paper/2203.16891/) (2022)
- [Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries](https://mlsanity.com/paper/2505.20451/) (2025)

## Abstract (arXiv)

The task of predicting dialog acts (DA) based on conversational dialog is a key component in the development of conversational agents. Accurately predicting DAs requires a precise modeling of both the conversation and the global tag dependencies. We leverage seq2seq approaches widely adopted in Neural Machine Translation (NMT) to improve the modelling of tag sequentiality. Seq2seq models are known to learn complex global dependencies while currently proposed approaches using linear conditional random fields (CRF) only model local tag dependencies. In this work, we introduce a seq2seq model tailored for DA classification using: a hierarchical encoder, a novel guided attention mechanism and beam search applied to both training and inference. Compared to the state of the art our model does not require handcrafted features and is trained end-to-end. Furthermore, the proposed approach achieves an unmatched accuracy score of 85% on SwDA, and state-of-the-art accuracy score of 91.6% on MRDA.