口语对话中上下文与反馈嵌入的联合学习
Joint Learning of Context and Feedback Embeddings in Spoken Dialogue
AI总结：
本文提出使用对比学习目标将简短对话上下文与反馈回应嵌入同一表示空间，该方法在美式英语对话的反馈排序任务中优于人类，且学到的嵌入包含了会话功能信息。
摘要：
简短的反馈回应（如反向频道）在口语对话中扮演着重要角色。迄今为止，大多数关于反馈回应的建模都集中在它们的时间点上，往往忽略了其词汇和韵律形式如何影响其上下文适宜性和会话功能。在本文中，我们研究了使用对比学习目标将简短的对话上下文和反馈回应嵌入到同一表示空间中的可能性。在我们的评估中，我们主要关注如何将此类嵌入用作上下文-反馈适宜性度量，从而用于美式英语对话中的反馈回应排序。我们的结果显示，在相同的排序任务下，该模型的表现优于人类，并且学习到的嵌入携带了关于反馈回应的会话功能的信息。
英文摘要：
Short feedback responses, such as backchannels, play an important role in spoken dialogue. So far, most of the modeling of feedback responses has focused on their timing, often neglecting how their lexical and prosodic form influence their contextual appropriateness and conversational function. In this paper, we investigate the possibility of embedding short dialogue contexts and feedback responses in the same representation space using a contrastive learning objective. In our evaluation, we primarily focus on how such embeddings can be used as a context-feedback appropriateness metric and thus for feedback response ranking in U.S. English dialogues. Our results show that the model outperforms humans given the same ranking task and that the learned embeddings carry information about the conversational function of feedback responses.
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。
