Leveraging Turn-taking Dynamics for Intent Recognition in Multi-party Conversations

Galo Castillo-López; Alexis Lombard; Gaël de Chalendar; Nasredine Semmar

cs.CLAug 28, 2026

Leveraging Turn-taking Dynamics for Intent Recognition in Multi-party Conversations

Authors: Galo Castillo-López, Alexis Lombard, Gaël de Chalendar, Nasredine Semmar

Organizations: Université Paris-Saclay, CEA, List, Palaiseau, France

Abstract

We propose a multi-task learning approach for multi-party dialogue intent recognition that leverages an auxiliary task that models turn-taking dynamics. Specifically, we introduce turn-transition entropy, a self-supervised target computed from the sequence of speaker transitions, which quantifies the predictability of interaction patterns. Experiments on multiple pre-trained models demonstrate that incorporating this auxiliary task improves intent recognition performance, outperforming existing approaches which ignore multi-party interaction dynamics. We find that our proposed continuous target can be learned as a single-task objective, suggesting that it is an actual signal carrying useful information.

Figures & tables

Figure 1: Examples of low- and high-entropy turn transitions. The top conversation follows a structured pattern of speaker transitions, presenting a lower turn-transition entropy. The bottom conversation exhibits more varied and less organized speaker transitions, leading to a higher entropy 2 2 2 We define the entropy computation in Section 3.3 . . Note that both examples have the same number of speakers and turn shifts.

Figure 2: Overview of our multitask learning approach architecture. Input representation includes model token embeddings; segment IDs to distinguish contextual from target utterances (i.e. latest turn utterance, to classify into any intent); and speaker embeddings to discriminate context uttered by the speaker producing the target utterance.

Figure 3: Entropy distributions computed on the training sets of MIntRec2.0 and MPGT.

		MPGT m		MIntRec2.0
Model	Method	F1	Acc.	F1	Acc.
BERT	CTX TEXT Zhang et al. (2024) 4 4 4 Performance metrics reported in the original paper.	- -	- -	53.61	59.04
	Label Space Reduction Castillo-López et al. (2025b)	71.38	91.73	41.92	41.66
	baseline (ours)	88.81	95.19	55.07	60.33
	TT Entropy Aux. Task (ours)	92.80	96.09	55.87	60.22
	Norm. TT Entropy Aux. Task (ours)	92.05	96.69	56.01	60.35

Table 1: Performance evaluation on the intent classification task. Scores correspond to the average macro F1 and accuracy over 5 runs. Scores in bold highlight the best performance on the same backbone model.

Method	F1	Acc.
He et al. (2021c)	70.90	79.15
Qamar et al. (2023)	72.49	80.72
baseline (ours)	73.54	81.00
TT Entropy Aux. Task (ours)	74.31	81.83
Norm. TT Entropy Aux. Task (ours)	74.78	81.95

Table 2: Evaluation on MEETInt with RoBERTa LARGE . Scores correspond to the average macro F1 and accuracy over 5 runs. Scores in bold highlight the best performance.

	MPGT		MIntRec2.0
Model	random	real	random	real
BERT	0.680	0.274	1.165	0.379
RoBERTa	0.677	0.205	1.161	0.428
DeBERTa	0.682	0.220	1.162	0.330

Table 3: Mean Absolute Error (MAE) on the regression target learned as a single task on real and random entropy values. Scores correspond to the average MAE over 5 runs. A lower MAE suggests an ease on the continuous variable learning.

Figure 4: Mean Absolute Error values along training epochs on MPGT validation set across all models.

Model	MPGT	MIntRec2.0
BERT	-8.84	-0.70
RoBERTa	-5.53	-0.29
DeBERTa	-0.41	-2.15

Table 4: Absolute difference in macro-F1 score of the classification task when replacing the auxiliary regression targets with randomly shuffled values during multitask training (

\mathrm{F1}_{\text{random}}-\mathrm{F1}_{\text{real}}

). Negative values indicate a classification performance degradation when training with random regression targets.

Dataset	$H$	$p$ -value	$\epsilon^{2}$
MPGT	51.57	$7.11\times 10^{-9}$	0.112
MIntRec2.0	155.15	$3.45\times 10^{-19}$	0.021

Table 5: Relationship analysis between the intent classes and the auxiliary variable. Kruskal-Wallis test results and effect sizes across datasets.

H

corresponds to the Kruskal–Wallis statistic, and

\epsilon^{2}

is the effect size

Appendix figures & tables9 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Property	Entropy	Norm. entropy
	turn index	0.69 *	0.46 *
MPGT	context length	0.08	0.01
	speaker count	0.66 *	0.20 *
	turn index	0.77 *	0.54 *
MIntRec2.0	context length	0.03	0.02
	speaker count	0.89 *	0.24 *

Appendix

Table 6: Spearman correlations between entropy measures and utterance properties. An asterisk (

*

) indicates

p<0.01

Panel of Figure 5 — Figure 5: Prompt template used on the LLM baseline for the intent classification task. Highlighted text in blue varies among dataset examples.

hyperparameter	value MPGT	value MIntRec2.0
eval_monitor	macro F1	macro F1
train_batch_size	16	16
eval_batch_size	16	16
test_batch_size	16	16
wait_patience	5	5
num_train_epochs	60	60

Appendix

Table 7: Set of hyperparameters used on BERT, RoBERTa, and DeBERTa fine-tuning baseline experiments.

hyperparameter	search range	step
weight $\lambda$	$[0.01,\,0.20]$	$0.01$
layer $l$	$[3,\,21]$	$1$

Appendix

Table 8: Optuna hyperparameter search space for the average weight

\lambda

and layer number l on the multi-task architecture.

hyperparameter	value MPGT	value MIntRec2.0
BERT
eval_monitor_main	macro F1	macro F1
eval_monitor_aux	MAE	MAE
train_batch_size	16	16
eval_batch_size	16	16
test_batch_size	16	16

Appendix

Table 9: Set of hyperparameters used on BERT, RoBERTa, and DeBERTa fine-tuning multi-task method experiments after Bayesian optimization.

	train	dev	test	labels
MPGT	.5K	.1K	.2K	8
MIntRec2.0	9.9K	1.8K	3.2K	30
MEETInt	81.9K	21.0K	31.8K	12

Appendix

Table 10: Number of examples per dataset split and number of labels on each corpus.

		MPGT		MIntRec2.0
Model	Input Representation	F1	Acc.	F1	Acc.
BERT	w/o context	86.84	95.04	53.08	58.67
	only target speaker	87.92	95.79	55.18	60.45
	all speakers w/o speaker emb.	87.69	94.69	54.74	59.94
	all speakers w. speaker emb.	90.65	95.49	55.36	60.57
RoBERTa	w/o context	81.85	93.83	55.44	59.85

Appendix

Table 11: Performance evaluation on the intent classification task using different input representation strategies. Scores correspond to the average macro F1 and accuracy over 5 runs. Scores in bold highlight the best performance on the same backbone model.

		MPGT		MIntRec2.0
Model	Method	F1	Acc.	F1	Acc.
RoBERTa BASE	Turn Modeling He et al. (2021c)	82.00	94.26	49.76	57.68
RoBERTa BASE	Turn Aware Speaker Graph Qamar et al. (2023)	83.30	95.19	52.31	57.70
RoBERTa LARGE	Turn Modeling He et al. (2021c)	73.64	92.92	51.40	56.40
RoBERTa LARGE	Turn Aware Speaker Graph Qamar et al. (2023)	81.28	94.29	52.82	57.92

Appendix

Table 12: Performance evaluation on the intent classification task. Comparison between RoBERTa BASE and RoBERTa LARGE on prior work baselines. Scores correspond to the average macro F1 and accuracy over 5 runs.

Figure 6: Distribution of the turn-transition entropy values across classes for MPGT.

Intent Classification

Intent classification assigns user utterances or behaviors to goals, supporting dialogue systems, search, safety decisions, and proactive assistance.

See all 60 papers

Proactive Dialogue Model with Intent Prediction
Apr 30, 2026Yang LuoLLM Prompting Spoken Dialogue Systems
Department of Computer Science University of Hong Kong
MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue
Oct 14, 2026Puneet Mathur, Dinesh ManochaTurn-Taking in Dialogue Full-Duplex Spoken Dialogue Systems
University of Maryland College Park, USA
Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue
Mar 12, 2026Kratika Bhagtani, Mrinal Anand, Yu Chen Xu +1Turn-Taking in Dialogue Turn-Taking Prediction
School of Electrical and Computer Engineering, Purdue University, United States · Ishiki Labs Inc.

Apr 30, 2026J/K move · Enter open · S save

Proactive Dialogue Model with Intent Prediction

Yang Luo

Department of Computer Science University of Hong Kong

LLM Prompting Spoken Dialogue Systems Task-Oriented Dialogue Systems

Open paper AskPDF arXiv

Dialogue models are inherently reactive, responding to the current user turn without anticipating upcoming intents, which leads to redundant interactions in multi-intent settings. We address this limitation by introducing a lightweight intent-transition prior derived from dialogue data and injected into the system prompt at inference time. We instantiate this prior using a Temporal Bayesian Network (T-BN) trained on per-turn intent annotations in MultiWOZ 2.2. The T-BN achieves Recall@5 = 0.787 and MRR = 0.576 on 1,071 held-out USER-turn pairs. In a ground-truth replay over 200 dialogues, BN-guided generation improves Coverage AUC from 0.742 to 0.856 and reduces the number of turns required to reach 75% intent coverage from 3.95 to 2.73. These results show that lightweight intent-transition guidance enables more proactive and efficient dialogue behavior without modifying the underlying language model.

Abstract

Intent Classification

Explore similar work

Proactive Dialogue Model with Intent Prediction

MultiPartyTurnBench: Benchmarking Floor Control in Multi-Party Spoken Dialogue

Speak or Stay Silent: Context-Aware Turn-Taking in Multi-Party Dialogue