Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback
This work addresses the challenge of enhancing semantic parsing accuracy for natural language processing applications, though it appears incremental by adapting existing counterfactual learning methods to this domain.
The paper tackled the problem of improving neural semantic parsers by applying counterfactual learning from logged human bandit feedback, resulting in significant improvements as demonstrated experimentally.
Counterfactual learning from human bandit feedback describes a scenario where user feedback on the quality of outputs of a historic system is logged and used to improve a target system. We show how to apply this learning framework to neural semantic parsing. From a machine learning perspective, the key challenge lies in a proper reweighting of the estimator so as to avoid known degeneracies in counterfactual learning, while still being applicable to stochastic gradient optimization. To conduct experiments with human users, we devise an easy-to-use interface to collect human feedback on semantic parses. Our work is the first to show that semantic parsers can be improved significantly by counterfactual learning from logged human feedback data.