Response-conditioned Turn-taking Prediction

Bing’er Jiang, Erik Ekstedt, Gabriel Skantze


Abstract
Previous approaches to turn-taking and response generation in conversational systems have treated it as a two-stage process: First, the end of a turn is detected (based on conversation history), then the system generates an appropriate response. Humans, however, do not take the turn just because it is likely, but also consider whether what they want to say fits the position. In this paper, we present a model (an extension of TurnGPT) that conditions the end-of-turn prediction on both conversation history and what the next speaker wants to say. We found that our model consistently outperforms the baseline model in a variety of metrics. The improvement is most prominent in two scenarios where turn predictions can be ambiguous solely from the conversation history: 1) when the current utterance contains a statement followed by a question; 2) when the end of the current utterance semantically matches the response. Treating the turn-prediction and response-ranking as a one-stage process, our findings suggest that our model can be used as an incremental response ranker, which can be applied in various settings.
Anthology ID:
2023.findings-acl.776
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
12241–12248
Language:
URL:
https://aclanthology.org/2023.findings-acl.776
DOI:
10.18653/v1/2023.findings-acl.776
Bibkey:
Cite (ACL):
Bing’er Jiang, Erik Ekstedt, and Gabriel Skantze. 2023. Response-conditioned Turn-taking Prediction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 12241–12248, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Response-conditioned Turn-taking Prediction (Jiang et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.776.pdf