An Imitation Game for Learning Semantic Parsers from User Interaction

Abstract

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.

arXiv commentAccepted to EMNLP 2020. 21 pages, 6 figures

References in corpus (7)

• On Calibration of Modern Neural Networks
• On the Convergence of Adam and Beyond
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• Interactive Policy Learning through Confidence-Based Autonomy
• A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions

Cited by in corpus (2)

• NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment
• Learning a Cost-Effective Annotation Policy for Question Answering