Learning as Conversation: Dialogue Systems Reinforced for Information Acquisition

TL;DR

This paper introduces a novel AI-powered dialogue system designed for knowledge acquisition through conversation, employing reinforced self-play to adapt across domains without needing in-domain data, and proven effective through extensive evaluations.

Contribution

The paper presents a new dialogue system that uses reinforced self-play for domain transfer and knowledge acquisition, enabling informative and attentive conversations without domain-specific training data.

Findings

Effective in delivering knowledge-intensive conversations

Substantially helps users gain knowledge without reading passages

Demonstrated success across three large public datasets

Abstract

We propose novel AI-empowered chat bots for learning as conversation where a user does not read a passage but gains information and knowledge through conversation with a teacher bot. Our information-acquisition-oriented dialogue system employs a novel adaptation of reinforced self-play so that the system can be transferred to various domains without in-domain dialogue data, and can carry out conversations both informative and attentive to users. Our extensive subjective and objective evaluations on three large public data corpora demonstrate the effectiveness of our system to deliver knowledge-intensive and attentive conversations and help end users substantially gain knowledge without reading passages. Our code and datasets are publicly available for follow-up research.