Learning When Not to Answer: A Ternary Reward Structure for Reinforcement Learning based Question Answering
This addresses a practical issue in real-world question-answering systems by improving confidence modeling, though it is incremental as it builds on prior binary reward structures.
The paper tackles the problem of reinforcement learning agents for question-answering over knowledge graphs by introducing a ternary reward structure that rewards agents for not answering when no answer is available, drastically improving precision while limiting unanswered questions.
In this paper, we investigate the challenges of using reinforcement learning agents for question-answering over knowledge graphs for real-world applications. We examine the performance metrics used by state-of-the-art systems and determine that they are inadequate for such settings. More specifically, they do not evaluate the systems correctly for situations when there is no answer available and thus agents optimized for these metrics are poor at modeling confidence. We introduce a simple new performance metric for evaluating question-answering agents that is more representative of practical usage conditions, and optimize for this metric by extending the binary reward structure used in prior work to a ternary reward structure which also rewards an agent for not answering a question rather than giving an incorrect answer. We show that this can drastically improve the precision of answered questions while only not answering a limited number of previously correctly answered questions. Employing a supervised learning strategy using depth-first-search paths to bootstrap the reinforcement learning algorithm further improves performance.