Towards a Continuous Knowledge Learning Engine for Chatbots

TL;DR

This paper introduces a novel continuous knowledge learning engine for chatbots, enabling them to learn and update knowledge interactively during conversations, modeled as an open-world knowledge base completion problem.

Contribution

It proposes a new lifelong interactive learning and inference (LiLi) technique that allows chatbots to acquire knowledge dynamically, improving their conversational capabilities.

Findings

LiLi demonstrates high promise in experimental evaluations.

Chatbots with LiLi become more knowledgeable over time.

The approach models knowledge learning as an open-world completion task.

Abstract

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.