Knowledge acquisition for dialogue agents using reinforcement learning on graph representations

TL;DR

This paper presents a reinforcement learning approach for dialogue agents to actively acquire and model new knowledge as RDF graphs during conversations, without explicit user feedback.

Contribution

It introduces a method for agents to learn policies for selecting graph patterns to enhance knowledge acquisition through dialogue.

Findings

Agents can effectively learn to select graph patterns for knowledge acquisition.

Reinforcement learning enables strategic information gathering without explicit feedback.

The approach demonstrates potential for scalable knowledge augmentation in dialogue systems.

Abstract

We develop an artificial agent motivated to augment its knowledge base beyond its initial training. The agent actively participates in dialogues with other agents, strategically acquiring new information. The agent models its knowledge as an RDF knowledge graph, integrating new beliefs acquired through conversation. Responses in dialogue are generated by identifying graph patterns around these new integrated beliefs. We show that policies can be learned using reinforcement learning to select effective graph patterns during an interaction, without relying on explicit user feedback. Within this context, our study is a proof of concept for leveraging users as effective sources of information.