检索结果-内蒙古大学图书馆

IEEE International Conference on Recent Advances in Systems Science and Engineering (RASSE)

作者： Wong, Albert Joiner, Dakota Chiu, Chunyin Elsayed, Mohamed Pereira, Keegan Khmelevsky, Youry Mahony, Joe Langara Coll Math & Stat Vancouver BC Canada Okanagan Coll Comp Sci Kelowna BC Canada Harris SmartWorks Res & Dev Ottawa ON Canada

ISBN: (纸本)9781665434416

With increasing complexity and volume of collected data continuing to rise, it is becoming ever more important to develop systems with high interactability. Businesses with an interest in big data continue to seek solutions that limit cost while providing effective, simplified solutions to current issues in data retrieval. Combined analysis and application of a multi-factorial system will likely lead to promising results in ease of reporting of complex data by nontechnical end users. This survey is focused on natural language processing (NLP) implementations for data query systems, especially related to massive data sets (1TB+) in OLTP databases, OLAP databases, and data warehouses. We are seeking the most up-to-date and effective uses of NLP for Speech-to-sql and text-to-sql generation, and the most recent advancements in data warehousing to optimize ELT efficiency and data retrieval, focusing on the highest performing code implementations on the Spider and Wikisql datasets. Many models, including sequence-to-sequence (seq2seq), sequence-to-sql (Seq2sql), and fuzzy semantic to sql (F-Semtosql), among others, are briefly described and compared. As well, recent advancements in data warehousing technology like multi-disk buffering in the ELT process and hybrid multi-dimensional and relational OLAP databases (HOLAPs) are discussed. The learning gathered here is applied to fill a gap in the current industrial knowledge base in service of increased efficiency in data access, retrieval, and reporting in a customer-facing environment.

关键词： Natural Language Processing Data Query System text-to-sql Speech-to-sql Deep Learning Machine Learning Human-Machine-Systems Energy Systems

来源：评论

学校读者我要写书评

暂无评论

Capturing sql Query Overlapping via Subtree Copy for Cross-Domain Context-Dependent sql Generation 25th

Capturing SQL Query Overlapping via Subtree Copy for Cross-D...

引用

25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

作者： Zhao, Ruizhuo Gao, Jinhua Shen, Huawei Cheng, Xueqi Chinese Acad Sci Inst Comp Technol CAS Key Lab Network Data Sci & Technol Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp & Control Engn Beijing 100049 Peoples R China

ISBN: (纸本)9783030757656;9783030757649

The key challenge of cross-domain context-dependent text-to-sql generation tasks lies in capturing the relation of natural language utterance and sql queries in different turns. A line of works attempt to combat this challenge by capturing the overlaps among consecutively generated sql queries. Existing models sequentially generate the sql query for a single turn and model the sql overlaps via copying tokens or segments generated in previous turns. However, they are not flexible enough to capture various overlapping granularities, e.g., columns, filters, or even the whole query, as they neglect the intrinsic structures inhabited in sql queries. In this paper, we employ tree-structured intermediate representations of sql queries, i.e., SemQL, for sql generation and propose a novel subtree-copy mechanism to characterize the sql overlaps. At each turn, we encode the interaction questions and previously generated trees as context and decode the SemQL tree in a top-down fashion. Each node is either generated according to SemQL grammar or copied from previously generated SemQL subtrees. Our model can capture various overlapping granularities by copying nodes at different levels of SemQL trees. We evaluate our approach on the SParC dataset and the experimental results show the superior performance of our model compared with state-of-the-art baselines.

关键词： Context-dependent text-to-sql Subtree-copy

来源：评论

学校读者我要写书评

暂无评论

Natural Language Data Interfaces: A Data Access Odyssey 27

Natural Language Data Interfaces: A Data Access Odyssey

引用

27th International Conference on Database Theory (ICDT)

作者： Koutrika, Georgia Athena Res Ctr Athens Greece

ISBN: (纸本)9783959773126

Back in 1970's, E. F. Codd worked on a prototype of a natural language question and answer application that would sit on top of a relational database system. Soon, natural language interfaces for databases (NLIDBs) became the holy grail for the database community. Different approaches have been proposed from the database, machine learning and NLP communities. Interest in the topic has had its peaks and valleys. After a long and adventurous journey of almost 50 years, there is a rekindled interest in NLIDBs in recent years, fueled by the need for democratizing data access and by the recent advances in deep learning and natural language processing in particular. There is a surge of works on natural language interfaces for databases using neural translation, and suddenly it becomes hard to keep up with advancements in the field. Are we close to finding the holy grail of data access? What are the lurking challenges that we need to surpass and what research opportunities arise? Finally, what is the role of the database community?

关键词： natural language data interfaces NLIDBs NL-to-sql text-to-sql conversational databases

来源：评论

学校读者我要写书评

暂无评论

Translating Natural Language Queries to sql Using the T5 Model 18

Translating Natural Language Queries to SQL Using the T5 Mod...

引用

18th Annual IEEE International Systems Conference (SysCon)

作者： Wong, Albert Pham, Lien Lee, Young Chan, Shek Sadaya, Razel Khmelevsky, Youry Clement, Mathias Cheng, Florence Wing Yau Mahony, Joe Ferri, Michael Langara Coll Math & Stat Vancouver BC Canada Okanagan Coll Math & Stat Kelowna BC Canada Okanagan Coll Comp Sci Kelowna BC Canada Harris SmartWorks Res & Dev Ottawa ON Canada

ISBN: (纸本)9798350358810;9798350358803

This paper presents the development process of a natural language to sql model using the T5 model as the basis. The models, developed in August 2022 for an online transaction processing system and a data warehouse, have a 73% and 84% exact match accuracy respectively. These models, in conjunction with other work completed in the research project, were implemented for several companies and used successfully on a daily basis. The approach used in the model development could be implemented in a similar fashion for other database environments and with a more powerful pre-trained language model.

关键词： Natural Language Processing Data Query System text-to-sql Speech-to-sql Deep Learning Machine Learning T5 Model Human-Machine-Systems Energy Systems

来源：评论

学校读者我要写书评

暂无评论

End-to-End Space-Efficient Pipeline for Natural Language Query based Spacecraft Health Data Analytics using Large Language Model (LLM) 5

End-to-End Space-Efficient Pipeline for Natural Language Que...

引用

5th International Conference on Innovative Trends in Information Technology (ICITIIT)

作者： Ram, Gummuluri Venkata Ravi Ashinee, Kesanam Kumar, M. Anand Natl Inst Technol Karnataka Dept Informat Technol Surathkal Karnataka India

ISBN: (纸本)9798350386813;9798350386820

There is a requirement of automated Space-craft Health monitoring and mission maintenance System which is able to process Natural-Language Query and revert back in required format for which size of space database is a hurdle. Hence, we propose an end-to-end customizable real-time pipeline for space mission health monitoring, utilizing LLM that addresses issue of very large databases by extracting only relevant columns in initial stages of pipeline itself leveraginf BERT for NER, LLM for fetching schema and PandasAI to execute these queries on large datasets efficiently, producing user-friendly outputs. The pipeline is robust, space-efficient, and customizable, offering features such as cross-table referencing and handling same feature names in multiple tables. We achieved 70% realtime accuracy.

关键词： BERT customizable LLM Natural-Language PandasAI sql space-craft space-efficient text-to-sql

来源：评论

学校读者我要写书评

暂无评论

Selecting and Generating Computational Meaning Representations for Short texts

Selecting and Generating Computational Meaning Representatio...

引用

作者： Finegan-Dollak, Catherine University of Michigan

学位级别：Ph.D.

Language conveys meaning, so natural language processing (NLP) requires representations of meaning. This work addresses two broad questions: (1) What meaning representation should we use? and (2) How can we transform text to our chosen meaning representation? In the first part, we explore different meaning representations (MRs) of short texts, ranging from surface forms to deep-learning-based models. We show the advantages and disadvantages of a variety of MRs for summarization, paraphrase detection, and clustering. In the second part, we use sql as a running example for an in-depth look at how we can parse text into our chosen MR. We examine the text-to-sql problem from three perspectives—methodology, systems, and applications—and show how each contributes to a fuller understanding of the task.

关键词： meaning representations semantics natural language processing text-to-sql Thesis

来源：评论

学校读者我要写书评

暂无评论

Intelligent Search Engine Technology for Power Dispatching Cloud Platform

Intelligent Search Engine Technology for Power Dispatching C...

引用

2023 IEEE International Conference on Electrical, Automation and Computer Engineering, ICEACE 2023

作者： Jiayang, Li Xiaolong, Jiang Ziyun, Chen Jie, Ding Lifei, Ren Jiangsu Nanjing210061 China

ISBN: (纸本)9798350309614

With the continuous deepening of energy transformation and the continuous promotion of electricity marketization reform, the structural form, system characteristics, and operational organization of the power system have undergone significant changes, and the power system has entered a new era. The design goal of intelligent search services is to provide a simple, efficient, reliable, and flexible search engine framework, providing comprehensive support for improving the search efficiency of users and applications. Through intelligent search services, three major indicators such as accuracy, coverage, and search speed can be effectively improved for users and applications. Intelligent search services provide search functions for structured and unstructured data, supporting visual display and intelligent sorting of search results. © 2023 IEEE.

关键词： deep learning Natural Language Processing Search text-to-sql

来源：评论

学校读者我要写书评

暂无评论

基于依存关系图注意力网络的sql生成方法

引用

浙江大学学报（工学版） 2024年第5期58卷 908-917页

作者：舒晴刘喜平谭钊李希万常选刘德喜廖国琼江西财经大学信息管理学院江西南昌330013 江西农业大学软件学院江西南昌330013

研究基于自然语言问题的结构化查询语言(sql)生成问题(text-to-sql).提出两阶段框架,旨在解耦模式链接和sql生成过程,降低sql生成的难度.第1阶段通过基于关系图注意力网络的模式链接器识别问题中提及的数据库表、列和值,利用问题的语法... 详细信息

研究基于自然语言问题的结构化查询语言(sql)生成问题(text-to-sql).提出两阶段框架,旨在解耦模式链接和sql生成过程,降低sql生成的难度.第1阶段通过基于关系图注意力网络的模式链接器识别问题中提及的数据库表、列和值,利用问题的语法结构和数据库模式项之间的内部关系,指导模型学习问题与数据库的对齐关系.构建问题图时,针对text-to-sql任务的特点,在原始句法依存树的基础上,合并与模式链接无关的关系,添加并列结构中的从属词与句中其他成分间的依存关系,帮助模型捕获长距离依赖关系.第2阶段进行sql生成,将对齐信息注入T5的编码器,对T5进行微调.在Spider、Spider-DK和Spider-Syn数据集上进行实验,实验结果显示,该方法具有良好的性能,尤其是对中等难度以上的text-to-sql问题具有良好的表现.

关键词： text-to-sql 自然语言查询依存句法分析关系图注意力网络

来源：评论

学校读者我要写书评

暂无评论

基于自然语言的数据库查询生成研究综述

引用

软件学报 2022年第11期33卷 4107-4136页

作者：刘喜平舒晴何佳壕万常选刘德喜江西财经大学信息管理学院江西南昌330013 江西农业大学软件学院江西南昌330013

数据库能够提供对大量数据的高效存储和访问,然而查询数据库需要掌握数据库查询语言sql,对于普通用户而言存在一定的门槛.基于自然语言的数据库查询(即text-to-sql)在最近几年受到了广泛的关注.对text-to-sql问题的当前进展进行了系统... 详细信息

数据库能够提供对大量数据的高效存储和访问,然而查询数据库需要掌握数据库查询语言sql,对于普通用户而言存在一定的门槛.基于自然语言的数据库查询(即text-to-sql)在最近几年受到了广泛的关注.对text-to-sql问题的当前进展进行了系统的分析.首先介绍了问题背景,并对问题进行了描述;其次,重点分析了目前提出的text-to-sql技术,包括基于流水线的方法、基于统计学习的方法,以及为多轮text-to-sql而开发的技术,对每种方法都进行了深入的分析和总结.再次,进一步讨论了text-to-sql所属的语义解析(semantic parsing)这一领域的研究.接着,总结了目前研究中广泛采用的数据集和评价指标,并从多个角度对主流模型进行了比较和分析.最后,总结了text-to-sql任务面临的挑战,以及未来的研究方向.

关键词：自然语言数据库查询 sql text-to-sql 语义解析自然语言处理

来源：评论

学校读者我要写书评

暂无评论

带复杂计算的金融领域自然语言查询的sql生成

引用

浙江大学学报（工学版） 2023年第2期57卷 277-286页

作者：何佳壕刘喜平舒晴万常选刘德喜廖国琼江西财经大学信息管理学院江西南昌330013

研究金融领域基于自然语言查询的结构化查询语言(sql)生成问题(text-to-sql),构建一个金融领域textto-sql数据集,称为SOFT数据集.该数据集覆盖了金融领域的常见查询,具有鲜明的特点,并对text-to-sql提出了挑战.提出金融领域text-to-sql... 详细信息

研究金融领域基于自然语言查询的结构化查询语言(sql)生成问题(text-to-sql),构建一个金融领域textto-sql数据集,称为SOFT数据集.该数据集覆盖了金融领域的常见查询,具有鲜明的特点,并对text-to-sql提出了挑战.提出金融领域text-to-sql模型Finsql,该模型优化了对金融领域复杂查询的支持.通过分析一类复杂计算查询(行计算查询)的特点,提出一种基于分治的方法,即先将一个行计算查询分解为若干个子查询,分别针对每个子查询生成sql语句,再将子查询的sql语句组合在一起得到原始查询的sql语句.在SOFT数据集上进行验证,结果显示,本研究所提的方法在复杂查询上效果优于已有方法.特别地,所提出的模型Finsql能够较好地支持行计算查询.

关键词： text-to-sql 自然语言查询金融领域行计算查询分治方法

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：