按年被提到
20172017 · 1 次2026
大模型与语言模型›大模型评测与真实性·arXiv:1709.00103 · cs.CL

Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

Victor Zhong, Caiming Xiong, Richard Socher · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-09-22 · 最近 2019-06-05
2不同的人
2活跃月份
2讨论串
733被引(OpenAlex)
arXiv 摘要(候选层不写导读)

A significant amount of the world's knowledge is stored in relational databases. However, the ability for users to retrieve facts from a database is limited due to a lack of understanding of query languages such as SQL. We propose Seq2SQL, a deep neural network for translating natural language questions to corresponding SQL queries. Our model leverages the structure of SQL queries to significantly reduce the output space of generated queries. Moreover, we use rewards from in-the-loop query execution over the database to learn a policy to generate unordered parts of the query, which we show are less suitable for optimization via cross entropy loss. In addition, we will publish WikiSQL, a dataset of 80654 hand-annotated examples of questions and SQL queries distributed across 24241 tables from Wikipedia. This dataset is required to train our model and is an order of magnitude larger than comparable datasets. By applying policy-based reinforcement learning with a query execution environment to WikiSQL, our model Seq2SQL outperforms attentional sequence to sequence models, improving execution accuracy from 35.9% to 59.4% and logical form accuracy from 23.4% to 48.3%.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论FiberBundle · 2019-06

“You can e.g. do this using semantic parsing, I remember some older papers but cannot find them right now. For a more recent paper see [1] (haven't read it though). You can also use Deep Learning for this. There are some interesting approaches using Reinforcement Learning [2] [1] https://www.aclweb.org/anthology/P18-1034 [2] https://arxiv.org/pdf/1709.001…”

Show HN: Translate English to SQL原评论 ↗
被提交为 story · 1 次