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 2108.13686cs.CL
收藏

基于知识的对话与奖励驱动的知识选择

Knowledge-Grounded Dialogue with Reward-Driven Knowledge Selection

Northeastern University(东北大学)

Shilei Liu, Xiaofeng Zhao, Bochao Li, Feiliang Ren

摘要:

基于知识的对话是一种基于会话语境和外部知识的会话,其中知识选择起着重要的作用,引起了越来越多的研究兴趣。然而,大多数现有的模型要么只选择一个知识或使用所有的知识生成响应。前者可能会在丢弃的知识中丢失有价值的信息,而后者可能会带来大量的噪声。同时,许多方法需要用指示地面实况知识的知识标签来训练知识选择器,但是这些标签难以获得并且需要大量的人工注释。基于这些问题,本文提出了一种基于强化学习的对话响应生成模型Knoforer,该模型可以自动从知识库中选择一个或多个相关知识,并且在训练过程中不需要知识标签。Knoformer在两个知识引导的会话数据集上进行了评估,并实现了最先进的性能。

英文摘要:

Knowledge-grounded dialogue is a task of generating a fluent and informative response based on both conversation context and a collection of external knowledge, in which knowledge selection plays an important role and attracts more and more research interest. However, most existing models either select only one knowledge or use all knowledge for responses generation. The former may lose valuable information in discarded knowledge, while the latter may bring a lot of noise. At the same time, many approaches need to train the knowledge selector with knowledge labels that indicate ground-truth knowledge, but these labels are difficult to obtain and require a large number of manual annotations. Motivated by these issues, we propose Knoformer, a dialogue response generation model based on reinforcement learning, which can automatically select one or more related knowledge from the knowledge pool and does not need knowledge labels during training. Knoformer is evaluated on two knowledge-guided conversation datasets, and achieves state-of-the-art performance.

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。

↑