# An Imitation Game for Learning Semantic Parsers from User Interaction

arXiv: https://arxiv.org/abs/2005.00689 · HTML: https://mlsanity.com/paper/2005.00689/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 May 2020.

## Built on by (most cited first, 23 of 23)

- [Exploring Chain-of-Thought Style Prompting for Text-to-SQL](https://mlsanity.com/paper/2305.14215/) (2023)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect](https://mlsanity.com/paper/2208.10099/) (2022)
- [Interactive Learning from Activity Description](https://mlsanity.com/paper/2102.07024/) (2021)
- [Interactive Grounded Language Understanding in a Collaborative Environment: IGLU 2021](https://mlsanity.com/paper/2205.02388/) (2022)
- [Continual Learning for Instruction Following from Realtime Feedback](https://mlsanity.com/paper/2212.09710/) (2022)
- [Text-to-SQL Error Correction with Language Models of Code](https://mlsanity.com/paper/2305.13073/) (2023)
- [Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing](https://mlsanity.com/paper/2305.08195/) (2023)
- [HELP ME THINK: A Simple Prompting Strategy for Non-experts to Create Customized Content with Models](https://mlsanity.com/paper/2208.08232/) (2022)
- [Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agents](https://mlsanity.com/paper/2403.05307/) (2024)
- [Learning Structural Edits via Incremental Tree Transformations](https://mlsanity.com/paper/2101.12087/) (2021)
- [NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment](https://mlsanity.com/paper/2110.06536/) (2021)
- [Simulating Bandit Learning from User Feedback for Extractive Question Answering](https://mlsanity.com/paper/2203.10079/) (2022)
- [Transforming Human-Centered AI Collaboration: Redefining Embodied Agents Capabilities through Interactive Grounded Language Instructions](https://mlsanity.com/paper/2305.10783/) (2023)
- [Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL](https://mlsanity.com/paper/2205.12422/) (2022)
- [Privacy-Preserving Domain Adaptation of Semantic Parsers](https://mlsanity.com/paper/2212.10520/) (2022)
- [Error Detection for Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2305.13683/) (2023)
- [SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL](https://mlsanity.com/paper/2506.04494/) (2025)
- [Reinforcement Learning for Generative AI: A Survey](https://mlsanity.com/paper/2308.14328/) (2023)
- [Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering](https://mlsanity.com/paper/2306.06779/) (2023)
- [Extending Multilingual Machine Translation through Imitation Learning](https://mlsanity.com/paper/2311.08538/) (2023)
- [IDAT: A Multi-Modal Dataset and Toolkit for Building and Evaluating Interactive Task-Solving Agents](https://mlsanity.com/paper/2407.08898/) (2024)
- [Underwater Robotics Semantic Parser Assistant](https://mlsanity.com/paper/2301.12134/) (2023)

## Abstract (arXiv)

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.