# Learning to Learn Semantic Parsers from Natural Language Supervision

arXiv: https://arxiv.org/abs/1902.08373 · HTML: https://mlsanity.com/paper/1902.08373/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2019.

## Built on by (most cited first, 7 of 7)

- [Interactive Learning from Activity Description](https://mlsanity.com/paper/2102.07024/) (2021)
- [Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing](https://mlsanity.com/paper/2305.08195/) (2023)
- [Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers](https://mlsanity.com/paper/2109.05186/) (2021)
- [Interpreting User Requests in the Context of Natural Language Standing Instructions](https://mlsanity.com/paper/2311.09796/) (2023)
- [Error-Aware Interactive Semantic Parsing of OpenStreetMap](https://mlsanity.com/paper/2106.11739/) (2021)
- [CorporateBench: Large-Scale Q&A Benchmarking with Temporal Knowledge Bases](https://mlsanity.com/paper/2608.27391/) (2026)
- [Technical Language Supervision for Intelligent Fault Diagnosis in Process Industry](https://mlsanity.com/paper/2112.07356/) (2021)

## Abstract (arXiv)

As humans, we often rely on language to learn language. For example, when corrected in a conversation, we may learn from that correction, over time improving our language fluency. Inspired by this observation, we propose a learning algorithm for training semantic parsers from supervision (feedback) expressed in natural language. Our algorithm learns a semantic parser from users' corrections such as "no, what I really meant was before his job, not after", by also simultaneously learning to parse this natural language feedback in order to leverage it as a form of supervision. Unlike supervision with gold-standard logical forms, our method does not require the user to be familiar with the underlying logical formalism, and unlike supervision from denotation, it does not require the user to know the correct answer to their query. This makes our learning algorithm naturally scalable in settings where existing conversational logs are available and can be leveraged as training data. We construct a novel dataset of natural language feedback in a conversational setting, and show that our method is effective at learning a semantic parser from such natural language supervision.