Lifelong and Continual Learning Dialogue Systems: Learning during Conversation

By Bing Liu, Sahisnu Mazumder. 2021

51 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Dialogue & Conversational AI, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Dialogue & Conversational AI

In Meta & Continual Learning

Citations in the corpus

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “The applications of continual learning in NLP are also highly diverse, such as dialogue system [130], [131], [260], [260], [282], [298], [437], text classification [87], [172], [325], [460], sentence generation [246], [298], [499], relation learning [343], [357], [455], [465], neural machine transla”
AI Autonomy: Self-initiated Open-world Continual Learning and Adaptation (2022, unknown): “Learning after deployment refers to learning continuously after the model has been deployed in an application or during model application (Liu and Mazumder 2021) on the fly.”
Lifelong Knowledge Learning in Rule-based Dialogue Systems (2020, background): “If knowledge can be acquired from users interactively during chatting, the chatbot will become more and more knowledgeable and powerful (Liu and Mazumder, 2021).”
SnapKV: LLM Knows What You are Looking for Before Generation (2024, background): “In practical applications such as chatbots and agents, where inputs can be multi-turn conversations, extensive articles or codebases [1, 9, 10], input sizes are often much larger than the sizes of generated responses, resulting in significant overhead.”
Continuous and Interactive Factual Knowledge Learning in Veriﬁcation Dialogues (2020, background): “See [27] for strategies on how to deal with incorrect knowledge from users.”
Self-Initiated Open World Learning for Autonomous AI Agents (2021, methodology): “Here we describe a dialogue system (called CML) that is based on the SOL framework and performs each function in SOL continually by itself after the system has been deployed (Mazumder et al. 2020; Liu and Mazumder 2021).”
Learning from data in the mixed adversarial non-adversarial case: Finding the helpers and ignoring the trolls (2022, background): “…a continual deployment of such a system can then potentially keep improving over time (Carlson et al., 2010; Kiela et al., 2021; Agichtein et al., 2006; Liu and Mazumder, 2021; Madotto et al., 2020; Shus-ter et al., 2020), constituting what Hancock et al. (2019) call a “self-feeding chatbot.””