TY - GEN
T1 - Graph enhanced cross-domain text-to-SQL generation
AU - Huo, Siyu
AU - Ma, Tengfei
AU - Chen, Jie
AU - Chang, Maria
AU - Wu, Lingfei
AU - Witbrock, Michael
N1 - Publisher Copyright:
© 2019 EMNLP-IJCNLP 2019 - Graph-Based Methods for Natural Language Processing - Proceedings of the 13th Workshop. All rights reserved.
PY - 2019
Y1 - 2019
N2 - Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations. Existing deep learning approaches for semantic parsing have shown promise on a variety of benchmark data sets, particularly on textto- SQL parsing. However, most text-to-SQL parsers do not generalize to unseen data sets in different domains. In this paper, we propose a new cross-domain learning scheme to perform text-to-SQL translation and demonstrate its use on Spider, a large-scale cross-domain text-to-SQL data set. We improve upon a state-of-the-art Spider model, SyntaxSQLNet, by constructing a graph of column names for all databases and using graph neural networks to compute their embeddings. The resulting embeddings offer better cross-domain representations and SQL queries, as evidenced by substantial improvement on the Spider data set compared to SyntaxSQLNet.
AB - Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations. Existing deep learning approaches for semantic parsing have shown promise on a variety of benchmark data sets, particularly on textto- SQL parsing. However, most text-to-SQL parsers do not generalize to unseen data sets in different domains. In this paper, we propose a new cross-domain learning scheme to perform text-to-SQL translation and demonstrate its use on Spider, a large-scale cross-domain text-to-SQL data set. We improve upon a state-of-the-art Spider model, SyntaxSQLNet, by constructing a graph of column names for all databases and using graph neural networks to compute their embeddings. The resulting embeddings offer better cross-domain representations and SQL queries, as evidenced by substantial improvement on the Spider data set compared to SyntaxSQLNet.
UR - https://www.scopus.com/pages/publications/85085049747
M3 - Conference contribution
AN - SCOPUS:85085049747
T3 - EMNLP-IJCNLP 2019 - Graph-Based Methods for Natural Language Processing - Proceedings of the 13th Workshop
SP - 159
EP - 163
BT - EMNLP-IJCNLP 2019 - Graph-Based Methods for Natural Language Processing - Proceedings of the 13th Workshop
PB - Association for Computational Linguistics (ACL)
T2 - 13th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2019, in conjunction with the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
Y2 - 4 November 2019 through 4 November 2019
ER -