# Speaker-change Aware CRF for Dialogue Act Classification

arXiv: https://arxiv.org/abs/2004.02913 · HTML: https://mlsanity.com/paper/2004.02913/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [Speaker and Time-aware Joint Contextual Learning for Dialogue-act Classification in Counselling Conversations](https://mlsanity.com/paper/2111.06647/) (2021)
- [DARER: Dual-task Temporal Relational Recurrent Reasoning Network for Joint Dialog Sentiment Classification and Act Recognition](https://mlsanity.com/paper/2203.03856/) (2022)
- [Abstractive Meeting Summarization: A Survey](https://mlsanity.com/paper/2208.04163/) (2022)
- [Relational Temporal Graph Reasoning for Dual-task Dialogue Language Understanding](https://mlsanity.com/paper/2306.09114/) (2023)
- [Transition-Matrix Regularization for Next Dialogue Act Prediction in Counselling Conversations](https://mlsanity.com/paper/2604.18539/) (2026)
- [NLP Research and Resources at DaSciM, Ecole Polytechnique](https://mlsanity.com/paper/2112.00566/) (2021)

## Abstract (arXiv)

Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. CRF models the conditional probability of the target DA label sequence given the input utterance sequence. However, the task involves another important input sequence, that of speakers, which is ignored by previous work. To address this limitation, this paper proposes a simple modification of the CRF layer that takes speaker-change into account. Experiments on the SwDA corpus show that our modified CRF layer outperforms the original one, with very wide margins for some DA labels. Further, visualizations demonstrate that our CRF layer can learn meaningful, sophisticated transition patterns between DA label pairs conditioned on speaker-change in an end-to-end way. Code is publicly available.