arXiv 2508.044032026-01-13cs.CL

基于语义相似度和语言模型预测置信度的对话响应预取

Dialogue Response Prefetching Based on Semantic Similarity and Prediction Confidence of Language Model

Nara Institute of Science and Technology（奈良科学技术研究所）；RIKEN（理化学研究所）；Tokyo Institute of Technology（东京技术大学）

Kiyotada Mori, Seiya Kawano, Angel Fernando Garcia Contreras, Koichiro Yoshino

备注：: Corrected typographical errors, including the number of subjects in the response evaluation experiment

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出基于语义相似度和语言模型预测置信度的对话响应预取方法，旨在减少用户感知延迟。

摘要：

对话响应预取已被研究以减少用户感知延迟（UPL），即用户在接收到系统响应前的等待时间，在口语对话系统中。为了减少UPL，有必要在用户说话结束前预测完整的用户话语，通常通过语言模型来准备预取的对话响应。在本研究中，我们提出了一种预测置信度模型（PCM），通过估计预测的完整用户话语与完整用户话语之间的语义相似度来确定预取是否可能。我们基于预测完整用户话语与完整用户话语之间的差异评估了我们的PCM。

英文摘要：

Prefetching of dialogue responses has been investigated to reduce user-perceived latency (UPL), which refers to the user's waiting time before receiving the system's response, in spoken dialogue systems. To reduce the UPL, it is necessary to predict complete user utterances before the end of the user's speech, typically by language models, to prepare prefetched dialogue responses. In this study, we proposed a prediction confidence model (PCM) that determines whether prefetching is possible or not by estimating the semantic similarity between the predicted complete user utterance and the complete user utterance. We evaluated our PCM based on the differences between the predicted complete user utterance and the complete user utterance.

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。