Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedback
Authors:
- Ahmed ElgoharyAEAhmed Elgohary
- Saghar HosseiniSHSaghar Hosseini
- Ahmed Hassan AwadallahAAAhmed Hassan Awadallah
Preprint
Abstract
We study the task of semantic parse correction with natural language feedback. Given a natural language utterance, most semantic parsing systems pose the problem as one-shot translation where the utterance is mapped to a corresponding logical form. In this paper, we investigate a more interactive scenario where humans can further interact with the system by providing free-form natural language feedback to correct the system when it generates an inaccurate interpretation of an initial utterance. We focus on natural language to SQL systems and construct, SPLASH, a dataset of utterances, incorrect SQL interpretations and the corresponding natural language feedback. We compare various reference models for the correction task and show that incorporating such a rich form of feedback can significantly improve the overall semantic parsing accuracy while retaining the flexibility of natural language interaction. While we estimated human correction accuracy is 81.5%, our best model achieves only 25.1%, which leaves a large gap for improvement in future research. SPLASH is publicly available at https://aka.ms/Splash_dataset.Keywords
All Related Versions
This publication has 3 references indexed in Scilit:
- Improving a Neural Semantic Parser by Counterfactual Learning from Human Bandit Feedback2018
- Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to ActionsTransactions of the Association for Computational Linguistics, 2013
- Natural language interfaces to databases – an introductionNatural Language Engineering, 1995