Learning from Executions for Semantic Parsing
This addresses the problem of reducing annotation costs for deploying neural semantic parsers in real-life applications, representing an incremental improvement over existing methods.
The paper tackles the bottleneck of expensive annotation in semantic parsing by proposing a semi-supervised learning method that encourages parsers to generate executable programs for unlabeled utterances, showing improved performance on Overnight and GeoQuery datasets and bridging the gap between semi-supervised and supervised learning.
Semantic parsing aims at translating natural language (NL) utterances onto machine-interpretable programs, which can be executed against a real-world environment. The expensive annotation of utterance-program pairs has long been acknowledged as a major bottleneck for the deployment of contemporary neural models to real-life applications. In this work, we focus on the task of semi-supervised learning where a limited amount of annotated data is available together with many unlabeled NL utterances. Based on the observation that programs which correspond to NL utterances must be always executable, we propose to encourage a parser to generate executable programs for unlabeled utterances. Due to the large search space of executable programs, conventional methods that use approximations based on beam-search such as self-training and top-k marginal likelihood training, do not perform as well. Instead, we view the problem of learning from executions from the perspective of posterior regularization and propose a set of new training objectives. Experimental results on Overnight and GeoQuery show that our new objectives outperform conventional methods, bridging the gap between semi-supervised and supervised learning.