arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2305.02036cs.CLcs.LG
收藏

基于响应条件的话轮转换预测

Response-conditioned Turn-taking Prediction

KTH Royal Institute of Technology(KTH皇家理工学院)

Bing'er Jiang, Erik Ekstedt, Gabriel Skantze

AI总结:

针对对话系统话轮转换两阶段处理的局限,提出融合对话历史与待生成响应的TurnGPT扩展模型,在多指标及两类模糊场景下优于基线,可作增量响应排序器使用。

摘要:

过往对话系统中的话轮转换与响应生成方法将其视为两阶段过程:首先(基于对话历史)检测话轮结束点,随后系统生成恰当响应。然而,人类并非仅因话轮可能结束就接过话头,还会考量自己想要表达的内容是否契合当前语境。本文提出一种基于TurnGPT(话轮生成式预训练Transformer)扩展的模型,该模型将话轮结束点预测同时建立在对话历史与下一位发言者想要表达的内容之上。我们发现该模型在多项指标上始终优于基线模型。在仅靠对话历史难以明确话轮预测结果的两类场景中,模型提升效果最为显著:1)当前话语包含陈述后接问题的情况;2)当前话语末尾与响应在语义上匹配的情况。研究结果表明,该模型将话轮预测与响应排序视为单阶段过程,可作为增量式响应排序器应用于多种场景。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑