Lifelong and Interactive Learning of Factual Knowledge in Dialogues

By Sahisnu Mazumder, Bing Liu, Shuai Wang, Nianzu Ma. 2019

28 citations recorded by the source corpus.

Dialogue systems are increasingly using knowledge bases (KBs) storing real-world facts to help generate quality responses. However, as the KBs are inherently incomplete and remain fixed during conversation, it limits dialogue systems’ ability to answer questions and to handle questions involving entities or relations that are not in the KB. In this paper, we make an attempt to propose an engine for Continuous and Interactive Learning of Knowledge (CILK) for dialogue systems to give them the ability to continuously and interactively learn and infer new knowledge during conversations. With more knowledge accumulated over time, they will be able to learn better and answer more questions. Our empirical evaluation shows that CILK is promising.

How researchers see this paper

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

1. Bing Liu
2. Sahisnu Mazumder
3. Zixuan Ke
4. Shuai Wang
5. Zheda Mai
6. Nianzu Ma
7. Ruiwen Li
8. C. Mei

Citations in the corpus

• Lifelong and Continual Learning Dialogue Systems: Learning during Conversation (2021, background): “In dialogue-based factual knowledge learning (Mazumder et al. 2019, 2020a), M is a factual inference model that is learned to infer new facts from existing (known) facts in the knowledge base (KB) in order to answer questions from the user.”
• Online Continual Learning in Image Classification: An Empirical Survey (2021, background): “Moreover, multiple works are proposed to address general CL language learning [138, 139] and specific language tasks, such as dialogue systems [140, 141, 142], image captioning [143], sentiment classification [144] and sentence representation learning [145].”
• Continual Lifelong Learning in Natural Language Processing: A Survey (2020, neutral): “, 2019) (Mazumder et al., 2019) (Liu, 2020)”
• Learning on the Job: Online Lifelong and Continual Learning (2020, methodology): “Ask when it does not understand something : Mazumder et al. (2019a) proposed a method to do this in the context of building natural language interfaces (NLI).”
• Deploying Lifelong Open-Domain Dialogue Learning (2020, methodology): “Related approaches have also been applied to the more limited case of question answering (Li et al., 2016b,c), or in simulation (Mazumder et al., 2019) as well.”
• An Application-Independent Approach to Building Task-Oriented Chatbots with Interactive Continual Learning (2020, background): “[19, 25] allow the learner to ask questions to users for factual knowledge learning.”
• Lifelong Knowledge Learning in Rule-based Dialogue Systems (2020, background): “nowledge Learning in Rule-based Dialogue Systems Bing Liu 1 and Chuhe Mei 2 1 University of Illinois at Chicago 2 Peking University liub@uic.edu 2 The most closely related works to ours are those in (Mazumder et al., 2019, 2020a), which attempt to build an engine for learning factual knowledge durin”
• Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job (2020, methodology): “Recently, Mazumder et al. (2019a) proposed a method to enable dialogue based language learning in the context of building NLIs.”
• Continuous and Interactive Factual Knowledge Learning in Verification Dialogues (2020, methodology): “The first part (called CILK) is presented in [31], which studies how to interactively learn new knowledge when the user asks a WH-question that the system is unable to answer.”