论文标题
通过及时调整建立个性化的对话系统
Building a Personalized Dialogue System with Prompt-Tuning
论文作者
论文摘要
没有一致响应的对话系统并不令人着迷。在这项研究中，我们建立了一个对话系统，可以根据给定的角色设置（角色）响应以带来一致性。考虑到语言模型迅速增加的趋势，我们提出了一种使用迅速调整的方法，该方法在预先训练的大规模语言模型上使用较低的学习成本。英语和日语中自动和手动评估的结果表明，可以使用比微调较少的计算资源来构建具有更自然和个性化响应的对话系统。
Dialogue systems without consistent responses are not fascinating. In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the trend of the rapidly increasing scale of language models, we propose an approach that uses prompt-tuning, which has low learning costs, on pre-trained large-scale language models. The results of automatic and manual evaluations in English and Japanese show that it is possible to build a dialogue system with more natural and personalized responses using less computational resources than fine-tuning.
