arXivDaily arXiv每日学术速递 周一至周五更新
​通知:联邦节假日调休:哥伦布日 / 原住民日(Columbus Day / Indigenous Peoples' Day),今日(13日)无更新。
arXiv 2211.06553cs.CLcs.AIcs.HCcs.LG

终身与持续学习对话系统

Lifelong and Continual Learning Dialogue Systems

Intel Labs(英特尔实验室);University of Illinois at Chicago (UIC)(伊利诺伊大学芝加哥分校);Indian Institute of Technology (IIT) - Roorkee(印度理工学院鲁尔基分校)

Sahisnu Mazumder, Bing Liu

AI总结:

本书提出终身学习对话系统范式,使聊天机器人能在与用户和环境的自主交互中持续学习语言、知识、样本与对话技能,并综述相关技术进展与未来挑战。

摘要:

对话系统(通常称为聊天机器人)近年来日益普及,因为它们被广泛应用于与用户进行闲聊对话,以及通过任务导向对话完成各种用户任务。现有聊天机器人通常基于预先收集并人工标注的数据进行训练,并且/或者使用手工编写的规则来构建;许多系统还使用人工编制的知识库(KBs)。它们理解自然语言的能力仍然有限,往往会产生许多错误,从而导致较差的用户满意度。通常情况下,它们需要工程师利用更多标注数据和更多人工编制的知识不断加以改进。本书介绍了终身学习对话系统这一新范式,旨在赋予聊天机器人通过自身主动发起的与用户及工作环境的交互而持续自主学习、从而改进自身的能力。随着系统与用户交谈得越来越多,或从外部来源学习得越来越多,它们会变得越来越有知识,也越来越擅长对话。本书介绍了构建此类持续学习对话系统的最新进展和技术:这些系统在对话过程中向用户学习新的语言表达、词汇知识和事实知识,在对话之外从外部来源学习这些内容,在对话过程中获取新的训练样本,并学习对话技能。除这些一般性主题外,本书还综述了关于对话系统某些特定方面持续学习的现有工作。本书最后讨论了未来研究面临的开放挑战。

英文摘要:

Dialogue systems, commonly known as chatbots, have gained escalating popularity in recent times due to their wide-spread applications in carrying out chit-chat conversations with users and task-oriented dialogues to accomplish various user tasks. Existing chatbots are usually trained from pre-collected and manually-labeled data and/or written with handcrafted rules. Many also use manually-compiled knowledge bases (KBs). Their ability to understand natural language is still limited, and they tend to produce many errors resulting in poor user satisfaction. Typically, they need to be constantly improved by engineers with more labeled data and more manually compiled knowledge. This book introduces the new paradigm of lifelong learning dialogue systems to endow chatbots the ability to learn continually by themselves through their own self-initiated interactions with their users and working environments to improve themselves. As the systems chat more and more with users or learn more and more from external sources, they become more and more knowledgeable and better and better at conversing. The book presents the latest developments and techniques for building such continual learning dialogue systems that continuously learn new language expressions and lexical and factual knowledge during conversation from users and off conversation from external sources, acquire new training examples during conversation, and learn conversational skills. Apart from these general topics, existing works on continual learning of some specific aspects of dialogue systems are also surveyed. The book concludes with a discussion of open challenges for future research.

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。

↑