关注对话间的间隔以改进长期对话生成
Mind the Gap Between Conversations for Improved Long-Term Dialogue Generation
AI总结：
本文提出让对话模型感知时间间隔，构建了多会话数据集GapChat，通过比较时间与事件进展的不同表示，证明时间感知模型在话题相关性和信息获取的评估指标上表现更优。
摘要：
知道如何随时间结束和恢复对话是交流的自然组成部分，使得讨论可以跨越数周、数月或数年。对话之间间隔的持续时间决定了哪些话题是相关的以及应该问哪些问题，而不显式建模时间的对话系统可能会生成不自然的回复。在本工作中，我们探索让对话模型感知时间的想法，并提出了GapChat，这是一个多会话对话数据集，其中每个会话之间的时间间隔是变化的。虽然数据集是实时构建的，但说话者生活中的事件进展是模拟的，以便创建跨越长时间跨度的现实对话。我们将时间信息暴露给模型，并比较了时间和事件进展的不同表示。在人类评估中，我们表明时间感知模型在判断所选话题相关性和从对话中获得信息的指标上表现更好。
英文摘要：
Knowing how to end and resume conversations over time is a natural part of communication, allowing for discussions to span weeks, months, or years. The duration of gaps between conversations dictates which topics are relevant and which questions to ask, and dialogue systems which do not explicitly model time may generate responses that are unnatural. In this work we explore the idea of making dialogue models aware of time, and present GapChat, a multi-session dialogue dataset in which the time between each session varies. While the dataset is constructed in real-time, progress on events in speakers' lives is simulated in order to create realistic dialogues occurring across a long timespan. We expose time information to the model and compare different representations of time and event progress. In human evaluation we show that time-aware models perform better in metrics that judge the relevance of the chosen topics and the information gained from the conversation.
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。
