arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2008.04759cs.CL
收藏

用于Text-to-SQL的混合排序网络

Hybrid Ranking Network for Text-to-SQL

Microsoft Dynamics 365 AI(微软 Dynamics 365 人工智能)

Qin Lyu, Kaushik Chakrabarti, Shobhit Hathi, Souvik Kundu, Jianwen Zhang, Zheng Chen

摘要:

在本文中,我们研究了如何在Text-to-SQL中利用预训练的语言模型。我们认为,以前的方法下利用基地语言模型的所有列连接在一起的NL问题,并将它们送入基地语言模型在编码阶段。我们提出了一种称为混合排名网络(HydraNet)的简洁方法,该方法将问题分解为列式排名和解码,最后通过简单的规则将列式输出组装成SQL查询。在这种方法中,编码器被给予NL问题和一个单独的列,其与训练BERT/RoBERTa的原始任务完全一致,因此我们避免了在现有方法中所必需的任何自组织池化或附加编码层。在WikiSQL数据集上的实验表明,该方法非常有效,取得了很好的效果。

英文摘要:

In this paper, we study how to leverage pre-trained language models in Text-to-SQL. We argue that previous approaches under utilize the base language models by concatenating all columns together with the NL question and feeding them into the base language model in the encoding stage. We propose a neat approach called Hybrid Ranking Network (HydraNet) which breaks down the problem into column-wise ranking and decoding and finally assembles the column-wise outputs into a SQL query by straightforward rules. In this approach, the encoder is given a NL question and one individual column, which perfectly aligns with the original tasks BERT/RoBERTa is trained on, and hence we avoid any ad-hoc pooling or additional encoding layers which are necessary in prior approaches. Experiments on the WikiSQL dataset show that the proposed approach is very effective, achieving the top place on the leaderboard.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑