An Imitation Game for Learning Semantic Parsers from User Interaction
This addresses the tedious process of data annotation and privacy risks in semantic parsing, offering an incremental improvement for developers and users in natural language processing applications.
The paper tackles the problem of bootstrapping and fine-tuning semantic parsers by proposing a human-in-the-loop methodology that learns directly from user interactions, using an imitation learning algorithm to improve performance on the text-to-SQL problem with promising empirical results.
Despite the widely successful applications, bootstrapping and fine-tuning semantic parsers are still a tedious process with challenges such as costly data annotation and privacy risks. In this paper, we suggest an alternative, human-in-the-loop methodology for learning semantic parsers directly from users. A semantic parser should be introspective of its uncertainties and prompt for user demonstration when uncertain. In doing so it also gets to imitate the user behavior and continue improving itself autonomously with the hope that eventually it may become as good as the user in interpreting their questions. To combat the sparsity of demonstration, we propose a novel annotation-efficient imitation learning algorithm, which iteratively collects new datasets by mixing demonstrated states and confident predictions and re-trains the semantic parser in a Dataset Aggregation fashion (Ross et al., 2011). We provide a theoretical analysis of its cost bound and also empirically demonstrate its promising performance on the text-to-SQL problem. Code will be available at https://github.com/sunlab-osu/MISP.