Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL
Ruiqi Zhong, Charlie Victor Snell, Dan Klein, Jason Eisner
Abstract
Can non-programmers annotate natural language utterances with complex programs that represent their meaning? We introduce APEL, a framework in which non-programmers select among candidate programs generated by a seed semantic parser (e.g., Codex). Since they cannot understand the candidate programs, we ask them to select indirectly by examining the programs' input-ouput examples. For each utterance, APEL actively searches for a simple input on which the candidate programs tend to produce different outputs. It then asks the non-programmers only to choose the appropriate output, thus allowing us to infer which program is correct and could be used to fine-tune the parser. As a first case study, we recruited human non-programmers to use APEL to re-annotate SPIDER, a text-to-SQL dataset. Our approach achieved the same annotation accuracy as the original expert annotators (75%) and exposed many subtle errors in the original annotations.
BibTeX
@inproceedings{
zhong2023nonprogrammers,
title={Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-{SQL}},
author={Ruiqi Zhong and Charlie Victor Snell and Dan Klein and Jason Eisner},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://openreview.net/forum?id=h1YhUpPKEq}
}