Recent advances in text-to-SQL: a survey of what we have and what we expect

N Deng, Y Chen, Y Zhang - arXiv preprint arXiv:2208.10099, 2022 - arxiv.org
Text-to-SQL has attracted attention from both the natural language processing and database
communities because of its ability to convert the semantics in natural language into SQL …

Learning contextual representations for semantic parsing with generation-augmented pre-training

P Shi, P Ng, Z Wang, H Zhu, AH Li, J Wang… - Proceedings of the …, 2021 - ojs.aaai.org
Most recently, there has been significant interest in learning contextual representations for
various NLP tasks, by leveraging large scale text corpora to train powerful language models …

Sadga: Structure-aware dual graph aggregation network for text-to-sql

R Cai, J Yuan, B Xu, Z Hao - Advances in Neural …, 2021 - proceedings.neurips.cc
The Text-to-SQL task, aiming to translate the natural language of the questions into SQL
queries, has drawn much attention recently. One of the most challenging problems of Text-to …

NL-EDIT: Correcting semantic parse errors through natural language interaction

A Elgohary, C Meek, M Richardson, A Fourney… - arXiv preprint arXiv …, 2021 - arxiv.org
We study semantic parsing in an interactive setting in which users correct errors with natural
language feedback. We present NL-EDIT, a model for interpreting natural language …

Towards robustness of text-to-SQL models against natural and realistic adversarial table perturbation

X Pi, B Wang, Y Gao, J Guo, Z Li, JG Lou - arXiv preprint arXiv:2212.09994, 2022 - arxiv.org
The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role
in delivering highly reliable applications. Previous studies along this line primarily focused …

Mt-teql: evaluating and augmenting neural nlidb on real-world linguistic and schema variations

P Ma, S Wang - Proceedings of the VLDB Endowment, 2021 - dl.acm.org
Natural Language Interface to Database (NLIDB) translates human utterances into SQL
queries and enables database interactions for non-expert users. Recently, neural network …

Trojansql: Sql injection against natural language interface to database

J Zhang, Y Zhou, B Hui, Y Liu, Z Li… - Proceedings of the 2023 …, 2023 - aclanthology.org
The technology of text-to-SQL has significantly enhanced the efficiency of accessing and
manipulating databases. However, limited research has been conducted to study its …

Benchmarking and improving text-to-sql generation under ambiguity

A Bhaskar, T Tomar, A Sathe, S Sarawagi - arXiv preprint arXiv …, 2023 - arxiv.org
Research in Text-to-SQL conversion has been largely benchmarked against datasets where
each text query corresponds to one correct SQL. However, natural language queries over …

Non-programmers can label programs indirectly via active examples: A case study with text-to-SQL

R Zhong, C Snell, D Klein, J Eisner - Proceedings of the 2023 …, 2023 - aclanthology.org
Can non-programmers annotate natural language utterances with complex programs that
represent their meaning? We introduce APEL, a framework in which non-programmers …

ConDA: state-based data augmentation for context-dependent text-to-SQL

D Wang, L Dou, W Che, J Wang, J Liu, L Li… - International Journal of …, 2024 - Springer
The context-dependent text-to-SQL task has profound real-world implications, as it facilitates
users in extracting knowledge from vast databases, which allows users to acquire the …