Paper Info
Title
Editing-based SQL Query Generation for Cross-Domain Context-Dependent Questions
Abstract
We focus on the cross-domain context-dependent text-to-SQL generation task. Based on the observation that adjacent natural language questions are often linguistically dependent and their corresponding SQL queries tend to overlap, we utilize the interaction history by editing the previous predicted query to improve the generation quality. Our editing mechanism views SQL as sequences and reuses generation results at the token level in a simple manner. It is flexible to change individual tokens and robust to error propagation. Furthermore, to deal with complex table structures in different domains, we employ an utterance-table encoder and a table-aware decoder to incorporate the context of the user utterance and the table schema. We evaluate our approach on the SParC dataset and demonstrate the benefit of editing compared with the state-of-the-art baselines which generate SQL from scratch. Our code is available at https://github.com/ryanzhumich/sparc_atis_pytorch.
Year
DOI
Venue
2019
10.18653/v1/D19-1537
EMNLP/IJCNLP (1)
DocType
Volume
Citations 
Conference
D19-1
2
PageRank 
References 
Authors
0.36
0
10
Name
Order
Citations
PageRank
Rui Zhang1688.10
Tao Yu2256.78
Heyang Er350.74
Sungrok Shim450.74
Eric Xue550.74
Victoria Lin6453.39
Tianze Shi7346.29
Caiming Xiong896969.56
Richard Socher96770230.61
Dragomir Radev1051.08