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 2503.02435cs.DB
收藏

NLI4DB:数据库自然语言接口的系统综述

NLI4DB: A Systematic Review of Natural Language Interfaces for Databases

Mengyi Liu, Jianqiu Xu

AI总结:

本文系统综述了数据库自然语言接口(NLIDB),将其翻译过程分为预处理、理解和翻译三阶段,并总结了相关方法、基准评估及LLM等前沿交互技术。

摘要:

随着各领域对数据库查询的需求不断增长,研究人员对数据库自然语言接口(NLIDB)投入了大量关注。本文对近期提出的 NLIDBs 进行了全面综述。我们首先简要介绍了自然语言处理技术、可执行数据库语言以及自然语言与可执行语言之间的中间表示,随后概述了从自然语言到可执行数据库语言的翻译过程。该翻译过程分为三个阶段:(i) 自然语言预处理,(ii) 自然语言理解,以及 (iii) 自然语言翻译。在预处理阶段,采用了传统方法和数据驱动方法。传统方法依赖于预定义的规则和语法,涉及的技术包括正则表达式、依存句法分析和命名实体识别。数据驱动方法依赖于大规模数据和机器学习模型,使用的技术包括词嵌入和模式链接。自然语言理解方法被分为三类:(i) 基于规则,(ii) 基于机器学习,以及 (iii) 混合方法。随后,我们描述了在关系数据库和时空数据库上构建可执行语言的通用过程。接着,介绍了将自然语言转换为可执行语言的常见基准和评估指标,并探讨了生成新基准的方法。最后,我们总结了 NLIDB 系统的分类、发展和增强,并讨论了与 NLIDB 相关的深度语言理解和数据库交互技术,包括 (i) 使用 LLM 执行 Text2SQL 任务,(ii) 从 SQL 生成自然语言解释,以及 (iii) 将语音查询转换为 SQL。

英文摘要:

As the demand for querying databases in all areas of life continues to grow, researchers have devoted significant attention to the natural language interface for databases (NLIDB). This paper presents a comprehensive survey of recently proposed NLIDBs. We begin with a brief introduction to natural language processing techniques, executable database languages and the intermediate representation between natural language and executable language, and then provide an overview of the translation process from natural language to executable database language. The translation process is divided into three stages: (i) natural language preprocessing, (ii) natural language understanding, and (iii) natural language translation. Traditional and data-driven methods are utilized in the preprocessing stage. Traditional approaches rely on predefined rules and grammars, and involve techniques such as regular expressions, dependency parsing and named entity recognition. Data-driven approaches depend on large-scale data and machine learning models, using techniques including word embedding and pattern linking. Natural language understanding methods are classified into three categories: (i) rule-based, (ii) machine learning-based, and (iii) hybrid. We then describe a general construction process for executable languages over relational and spatio-temporal databases. Subsequently, common benchmarks and evaluation metrics for transforming natural language into executable language are presented, and methods for generating new benchmarks are explored. Finally, we summarize the classification, development, and enhancement of NLIDB systems, and discuss deep language understanding and database interaction techniques related to NLIDB, including (i) using LLM for Text2SQL tasks, (ii) generating natural language interpretations from SQL, and (iii) transforming speech queries into SQL.

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。

↑