A Coordination-based Approach for Focused Learning in Knowledge-Based Systems
This addresses an incremental optimization issue for developers of knowledge-based systems like Learning by Reading and Machine Reading systems.
The paper tackles the problem of selecting optimal learning requests for knowledge-based systems to maximize question-answering performance, showing that using a reinforcement learning approach based on coordination game theory can significantly improve results.
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.