Search Results for author: John R. Woodward

Found 4 papers, 2 papers with code

Natural SQL: Making SQL Easier to Infer from Natural Language Specifications

3 code implementations Findings (EMNLP) 2021 Yujian Gan, Xinyun Chen, Jinxia Xie, Matthew Purver, John R. Woodward, John Drake, Qiaofu Zhang

Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation.

Text-To-SQL Translation

Towards Robustness of Text-to-SQL Models against Synonym Substitution

1 code implementation ACL 2021 Yujian Gan, Xinyun Chen, Qiuping Huang, Matthew Purver, John R. Woodward, Jinxia Xie, Pengsheng Huang

We observe that the accuracy dramatically drops by eliminating such explicit correspondence between NL questions and table schemas, even if the synonyms are not adversarially selected to conduct worst-case adversarial attacks.

Text-To-SQL

Evolution of Group-Theoretic Cryptology Attacks using Hyper-heuristics

no code implementations15 Jun 2020 Matthew J. Craven, John R. Woodward

Hyper-heuristics are a way to generate new algorithms from existing algorithm components (in this case the simple heuristics), with the EAs being one example of the type of algorithm which can be generated by our hyper-heuristic framework.

Cannot find the paper you are looking for? You can Submit a new open access paper.