.png){kind=icon}
.png){kind=icon}
Return
Match matrix aggregation enhanced transition-based neural network or SQL parsing
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neucom.2021.03.005.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Nowadays many neural networks have been widely employed for semantic parsing problems especially for Structured Query Language (SQL) parsing, which aims at transforming natural language sentences into SQL representations. Selecting proper table headers in SQL tasks is extremely important, and the main cause of performance drop is that attention mechanism in neural models sometimes obtains wrong word-level distribution over headers. In order to obtain better header selection, we propose a match matrix aggregation enhanced SQL parser to consider the outer character-level ROUGE-L match informa-tion between the question and headers, then dynamically combine it with the inner generated attention matrix. We also introduce customized BERT and extra semantic information of the question and headers to further improve the performance. The results on two SQL datasets demonstrate that our method achieves an inspiring performance and highly outperforms other state-of-the-art alternatives. (c) 2021 Elsevier B.V. All rights reserved.
Keywords:
SQL parsing
Match matrix aggregation
Character-level ROUGE-L
Generated attention matrix
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.