Towards a Continuous Knowledge Learning Engine for Chatbots
By Sahisnu Mazumder, Nianzu Ma, B. Liu. 2018
23 citations recorded by the source corpus.
Although chatbots have been very popular in recent years, they still have some serious weaknesses which limit the scope of their applications. One major weakness is that they cannot learn new knowledge during the conversation process, i.e., their knowledge is fixed beforehand and cannot be expanded or updated during conversation. In this paper, we propose to build a general knowledge learning engine for chatbots to enable them to continuously and interactively learn new knowledge during conversations. As time goes by, they become more and more knowledgeable and better and better at learning and conversation. We model the task as an open-world knowledge base completion problem and propose a novel technique called lifelong interactive learning and inference (LiLi) to solve it. LiLi works by imitating how humans acquire knowledge and perform inference during an interactive conversation. Our experimental results show LiLi is highly promising.
Subfields: Artificial Intelligence, Natural Language Processing, LLM Agents & Tool Use
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
- Jason Aaron Edward Weston
- Bing Liu
- Chenguang Zhu
- Sahisnu Mazumder
- Mohit Bansal
- Jianfeng Gao
- Antoine Bordes
- Heng Ji
In Natural Language Processing
- Jason Aaron Edward Weston
- Antoine Bordes
- Chenguang Zhu
- Bing Liu
- Mohit Bansal
- Jianfeng Gao
- Kurt Shuster
- Sahisnu Mazumder
In LLM Agents & Tool Use
Citations in the corpus
- Learning from Dialogue after Deployment: Feed Yourself, Chatbot! (2019, background): “There are other, somewhat less related, ways to use feedback during dialogue for learning, notably for collecting knowledge to answer questions (Mazumder et al., 2018; Hixon et al., 2015; Pappu and Rudnicky, 2013), and more commonly in re-”
- Lifelong and Interactive Learning of Factual Knowledge in Dialogues (2019, unknown): “We reported a priliminary research in (Mazumder et al., 2018).”
- Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job (2020, background): “Some preliminary work has been done on (1) and (2) in (Mazumder, Ma, and Liu 2018; Mazumder et al. 2019a,b).”
- A Survey of Knowledge-enhanced Text Generation (2020, background): “A meaningful exploration of was discussed in [86].”