Lifelong and Continual Learning Dialogue Systems: Learning during Conversation
Lifelong and Continual Learning Dialogue Systems: Learning during Conversation
复制标题
DOI：
10.1609/aaai.v35i17.17768
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Bing Liu;S. Mazumder
中科院分区：
文献类型：
--
作者：
Bing Liu;S. Mazumder
对话系统，也被称为聊天机器人，现在被广泛应用。然而，他们仍然有一些主要的弱点。一个关键的弱点是，它们通常是从手动标记的数据和/或用手工编写的规则进行训练的，而且它们的知识库（KBs）也是由人类专家编译的。由于涉及大量的人工工作，它们难以扩展，并且由于其理解自然语言的能力有限以及知识库中的知识有限，往往会产生许多错误。因此，用户满意程度往往很低。在本文中，我们建议通过赋予聊天机器人不断学习(1)新的世界知识的能力，(2)新的语言表达，以使他们能够采取行动，(3)新的会话技能，从而大大改善这种情况，从而使他们在与用户进行越来越多的聊天时，他们变得越来越有知识，越来越能够理解各种自然语言表达，并提高他们的会话技能。
Dialogue systems, also called chatbots, are now used in a wide range of applications. However, they still have some major weaknesses. One key weakness is that they are typically trained from manually-labeled data and/or written with handcrafted rules, and their knowledge bases (KBs) are also compiled by human experts. Due to the huge amount of manual effort involved, they are difficult to scale and also tend to produce many errors ought to their limited ability to understand natural language and the limited knowledge in their KBs. Thus, the level of user satisfactory is often low. In this paper, we propose to dramatically improve the situation by endowing the chatbots the ability to continually learn (1) new world knowledge, (2) new language expressions to ground them to actions, and (3) new conversational skills, during conversation by themselves so that as they chat more and more with users, they become more and more knowledgeable and are better and better able to understand diverse natural language expressions and to improve their conversational skills.