Response-conditioned Turn-taking Prediction
This work addresses turn-taking ambiguity in conversational AI systems, offering a more human-like approach, though it is incremental as it builds on existing models like TurnGPT.
The paper tackles the problem of turn-taking prediction in conversational systems by conditioning end-of-turn predictions on both conversation history and the intended response, rather than treating it as a two-stage process. The model consistently outperforms baselines, with notable improvements in ambiguous scenarios like statements followed by questions or semantic matches between utterance ends and responses.
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.