Knowledge Commons of Institute of Automation,CAS
Leveraging Explicit Lexico-logical Alignments in Text-to-SQL Parsing | |
Sun, Runxin1,2![]() ![]() ![]() ![]() | |
2022-05 | |
会议名称 | Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL 2022) |
会议日期 | May 22–27, 2022 |
会议地点 | Dublin |
会议举办国 | Ireland |
摘要 | Text-to-SQL aims to parse natural language questions into SQL queries, which is valuable in providing an easy interface to access large databases. Previous work has observed that leveraging lexico-logical alignments is very helpful to improve parsing performance. However, current attention-based approaches can only model such alignments at the token level and have unsatisfactory generalization capability. In this paper, we propose a new approach to leveraging explicit lexico-logical alignments. It first identifies possible phrase-level alignments and injects them as additional contexts to guide the parsing procedure. Experimental results on Squall show that our approach can make better use of such alignments and obtains an absolute improvement of 3.4% compared with the current state-of-the-art. |
收录类别 | EI |
语种 | 英语 |
EI入藏号 | 20223612688289 |
EI分类号 | 601.1 |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/56607 |
专题 | 复杂系统认知与决策实验室 |
通讯作者 | He, Shizhu |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China 3.AI Lab, China Merchant Bank, ShenZhen, 518057, China 4.Beijing Academy of Artificial Intelligence, Beijing, 100084, China |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Sun, Runxin,He, Shizhu,Zhu, Chong,et al. Leveraging Explicit Lexico-logical Alignments in Text-to-SQL Parsing[C],2022. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
2022.acl-short.31.pd(528KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论