Data-Anonymous Encoding for Text-to-SQL Generation

Zhen Dong, Shizhao Sun, Hongzhi Liu, Jian-Guang Lou, Dongmei Zhang


Abstract
On text-to-SQL generation, the input utterance usually contains lots of tokens that are related to column names or cells in the table, called table-related tokens. These table-related tokens are troublesome for the downstream neural semantic parser because it brings complex semantics and hinders the sharing across the training examples. However, existing approaches either ignore handling these tokens before the semantic parser or simply use deterministic approaches based on string-match or word embedding similarity. In this work, we propose a more efficient approach to handle table-related tokens before the semantic parser. First, we formulate it as a sequential tagging problem and propose a two-stage anonymization model to learn the semantic relationship between tables and input utterances. Then, we leverage the implicit supervision from SQL queries by policy gradient to guide the training. Experiments demonstrate that our approach consistently improves performances of different neural semantic parsers and significantly outperforms deterministic approaches.
Anthology ID:
D19-1543
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5405–5414
Language:
URL:
https://aclanthology.org/D19-1543
DOI:
10.18653/v1/D19-1543
Bibkey:
Cite (ACL):
Zhen Dong, Shizhao Sun, Hongzhi Liu, Jian-Guang Lou, and Dongmei Zhang. 2019. Data-Anonymous Encoding for Text-to-SQL Generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5405–5414, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Data-Anonymous Encoding for Text-to-SQL Generation (Dong et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1543.pdf