Annotated speech corpora are databases consisting of signal data along with time-aligned symbolic `transcriptions'. Such databases are typically multidimensional, heterogeneous and dynamic. These properties present a number of tough challenges for representation and query. The temporal nature of the data adds an additional layer of complexity. This paper presents and harmonises two independent efforts to model annotated speech databases, one at Macquarie University and one at the University of Pennsylvania. Various query languages are described, along with illustrative applications to a variety of analytical problems. The research reported here forms a part of several ongoing projects to develop platform-independent open-source tools for creating, browsing, searching, querying and transforming linguistic databases, and to disseminate large linguistic databases over the internet.
DBCopilot: Natural Language Querying over Massive Databases via Schema Routing
Institute of Software, CAS(中国科学院软件研究所);Hangzhou Institute for Advanced Study, UCAS(中国科学院大学杭州高等研究院);University of Chinese Academy of Sciences (UCAS)(中国科学院大学);Alibaba Cloud Intelligence Group(阿里巴巴云智能集团)
Sonar-TS: Search-Then-Verify Natural Language Querying for Time Series Databases
Jiangxi University of Finance and Economics(江西财经大学);Griffith University(格里菲斯大学);Yunnan University(云南大学);Microsoft Research Asia(微软亚洲研究院);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
TableQuery: Querying tabular data with natural language
Saama(萨玛);Activeloop(活跃循环);Oregon State University(俄勒冈州立大学)
本文介绍了TableQuery,这是一种使用预训练的深度学习模型来查询表格数据的新工具,用于回答自由文本的问题。针对表格数据的问答的现有深度学习方法具有各种局限性,例如必须将整个表格作为输入馈送到神经网络模型中,这使得它们不适合大多数现实世界的应用。由于真实世界的数据可能包含数百万行,因此可能无法完全放入内存中。此外,数据可以存储在实时更新的实时数据库中,并且每次更新时将整个数据库串行化为神经网络友好格式是不切实际的。在TableQuery中,我们使用针对自由文本问答预先训练的深度学习模型,将自然语言查询转换为结构化查询,可以针对数据库或电子表格运行。这种方法消除了将整个数据装入内存以及序列化数据库的需要。此外,针对自由文本问答预训练的深度学习模型可以在HuggingFace Model Hub(7)等平台上轻松获得。TableQuery不需要重新训练;当新训练的问答模型具有更好的性能时,它可以替换TableQuery中的现有模型。
Adaptations of AI models for querying the LandMatrix database in natural language
INRAE(法国国家农业、食品与环境研究院);CIRAD(法国国际农业发展研究中心);TETIS(TETIS机构);Univ. Montpellier(蒙彼利埃大学);AgroParisTech(巴黎农业科技学院);CNRS(法国国家科学研究中心);International Land Coalition(国际土地联盟)
VGStore: A Multimodal Extension to SPARQL for Querying RDF Scene Graph
Wangxuan Institute of Computer Technology (WICT), Peking University(北京大学王选计算机研究所);Beijing Institute for General Artificial Intelligence (BIGAI)(北京通用人工智能研究院)
Text-to-OverpassQL: A Natural Language Interface for Complex Geodata Querying of OpenStreetMap
School of Informatics, University of Edinburgh(爱丁堡大学信息学院);Computational Linguistics, Heidelberg University(海德堡大学计算语言学系);IWR, Heidelberg University(海德堡大学应用科学计算研究所)
Benchmarking Hybrid Deep Research Across Database Querying and Web Search
University of Houston(休斯顿大学);University of California, Los Angeles(加州大学洛杉矶分校);The University of Hong Kong(香港大学);Seoul National University(首尔大学);Snowflake AI Research(Snowflake AI研究院)
CityLLM: A framework for natural-language querying of semantic 3D city models
GRID Lab, School of Built Environment, UNSW Sydney(新南威尔士大学悉尼分校建筑环境学院GRID实验室);School of Civil and Environmental Engineering, UNSW Sydney(新南威尔士大学悉尼分校土木与环境工程学院)
研究针对语义 3D 城市模型访问查询难的问题,提出 CityLLM 框架,结合空间与图形数据库,在基于语言模型工作流中支持迭代查询等。通过多种模型在鹿特丹数据集上评估,多个场景 54 个查询显示其性能强大,为语义 3D 城市数据对话访问提供轻量级可扩展方法。
CEFR-Annotated WordNet: LLM-Based Proficiency-Guided Semantic Database for Language Learning
Nagoya Institute of Technology(名古屋技术大学);Kitami Institute of Technology(Kitami技术学院);Chitose Institute of Science and Technology(常立科学技术学院);Hokkaido University(北海道大学)