Lifelong and Interactive Learning of Factual Knowledge in Dialogues

Abstract

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.

arXiv commentPublished in SIGDIAL 2019

References in corpus (11)

• A Review of Relational Machine Learning for Knowledge Graphs
• A Neural Conversational Model
• Large-scale Simple Question Answering with Memory Networks
• Topic Aware Neural Response Generation
• A Survey of Available Corpora for Building Data-Driven Dialogue Systems
• Response Ranking with Deep Matching Networks and External Knowledge in Information-seeking Conversation Systems
• Dialogue Learning With Human-In-The-Loop
• Context-aware Path Ranking for Knowledge Base Completion
• Towards a Continuous Knowledge Learning Engine for Chatbots
• LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues
• Listen, Interact and Talk: Learning to Speak via Interaction

Cited by in corpus (5)

• Lifelong Knowledge Learning in Rule-based Dialogue Systems
• Deploying Lifelong Open-Domain Dialogue Learning
• Evaluate On-the-job Learning Dialogue Systems and a Case Study for Natural Language Understanding
• Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job
• Online Continual Learning in Image Classification: An Empirical Survey