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 2106.06139cs.CLcs.AIcs.LG
收藏

基于检索的聊天机器人构建的全面解决方案

A comprehensive solution to retrieval-based chatbot construction

Monash Biomedical Imaging, Monash University, Australia(墨尔本大学生物医学成像中心,墨尔本大学,澳大利亚);Department of Computer Science and Information Technology, La Trobe University, Australia(拉特鲁布大学计算机科学与信息技术系,拉特鲁布大学,澳大利亚)

Kristen Moore, Shenjun Zhong, Zhen He, Torsten Rudolf, Nils Fisher, Brandon Victor, Neha Jindal

AI总结:

本文提出了一套从无标签聊天记录到部署的端到端基于检索的聊天机器人构建解决方案,核心是采用自监督对比学习训练的层次化RNN回复选择模型,实验证明其优于弱监督分类模型。

摘要:

在本文中,我们展示了训练和部署一个基于检索的聊天机器人的实验结果,该机器人通过对比学习进行自监督训练,旨在协助客户支持代理。与该领域大多数仅关注解决可部署聊天机器人单一组件的现有研究论文不同,我们提出了一套端到端的解决方案,引导读者从无标签聊天记录出发,最终构建出可部署的聊天机器人。这套解决方案包括从聊天记录中创建自监督数据集和弱标注数据集,以及选择固定预设回复列表的系统方法。我们为回复选择模型提出了一种基于层次结构的 RNN 架构,选择该架构是因为它能够缓存中间话语嵌入,这有助于满足部署推理速度的要求。我们比较了该架构在 3 种不同学习目标下的性能:自监督对比学习、二分类和多分类。我们发现,使用自监督对比学习模型优于在弱标注数据集上训练的二分类和多分类模型。我们的结果验证了自监督对比学习方法可以有效地用于真实世界的聊天机器人场景。

英文摘要:

In this paper we present the results of our experiments in training and deploying a self-supervised retrieval-based chatbot trained with contrastive learning for assisting customer support agents. In contrast to most existing research papers in this area where the focus is on solving just one component of a deployable chatbot, we present an end-to-end set of solutions to take the reader from an unlabelled chatlogs to a deployed chatbot. This set of solutions includes creating a self-supervised dataset and a weakly labelled dataset from chatlogs, as well as a systematic approach to selecting a fixed list of canned responses. We present a hierarchical-based RNN architecture for the response selection model, chosen for its ability to cache intermediate utterance embeddings, which helped to meet deployment inference speed requirements. We compare the performance of this architecture across 3 different learning objectives: self-supervised contrastive learning, binary classification, and multi-class classification. We find that using a self-supervised contrastive learning model outperforms training the binary and multi-class classification models on a weakly labelled dataset. Our results validate that the self-supervised contrastive learning approach can be effectively used for a real-world chatbot scenario.

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。

↑