Response-conditioned Turn-taking Prediction

TL;DR

This paper introduces a model that predicts turn-taking in conversations by considering both conversation history and the speaker's intended response, improving accuracy in ambiguous scenarios.

Contribution

It extends TurnGPT to condition turn prediction on both dialogue context and anticipated response, enhancing performance in complex turn-taking situations.

Findings

Outperforms baseline models in multiple metrics

Most improvements occur when turn cues are ambiguous

Can serve as an incremental response ranker

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.