A Coordination-based Approach for Focused Learning in Knowledge-Based Systems

TL;DR

This paper introduces a coordination-based reinforcement learning approach to optimize the selection of learning requests in knowledge-based systems, significantly enhancing question-answering performance.

Contribution

It models the selection of learning requests as a coordination game and applies reinforcement learning to improve knowledge acquisition strategies.

Findings

Reinforcement learning effectively improves Q/A performance.

Coordination game modeling captures the dynamics of learning request selection.

Significant performance gains demonstrated through experiments.

Abstract

Recent progress in Learning by Reading and Machine Reading systems has significantly increased the capacity of knowledge-based systems to learn new facts. In this work, we discuss the problem of selecting a set of learning requests for these knowledge-based systems which would lead to maximum Q/A performance. To understand the dynamics of this problem, we simulate the properties of a learning strategy, which sends learning requests to an external knowledge source. We show that choosing an optimal set of facts for these learning systems is similar to a coordination game, and use reinforcement learning to solve this problem. Experiments show that such an approach can significantly improve Q/A performance.