arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1909.00786cs.CL
收藏

基于编辑的跨域上下文相关问题的SQL查询生成

Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions

Yale University(耶鲁大学);Salesforce Research(赛富时研究院);Cornell University(康奈尔大学)

Rui Zhang, Tao Yu, He Yang Er, Sungrok Shim, Eric Xue, Xi Victoria Lin, Tianze Shi, Caiming Xiong, Richard Socher, Dragomir Radev

摘要:

我们专注于跨域上下文相关的文本到SQL生成任务。基于相邻的自然语言问题往往是语言依赖的,其相应的SQL查询往往重叠的观察,我们利用编辑以前的预测查询的交互历史,以提高生成质量。我们的编辑机制将SQL视为序列,并以简单的方式在令牌级别重用生成结果。它可以灵活地更改单个令牌,并且对错误传播具有鲁棒性。此外,为了处理不同领域中的复杂表结构,我们采用了一个话语表编码器和一个表感知解码器,将用户话语的上下文和表模式。我们在SParC数据集上评估了我们的方法,并证明了与从头开始生成SQL的最先进基线相比,编辑的好处。我们的代码可在https://github.com/ryanzhumich/sparc_atis_pytorch上获得。

英文摘要:

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.

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。

↑