Analytics on structured data is a mature field with many successful methods. However, most real world data exists in unstructured form, such as images and conversations. We investigate the potential of Large Language Models (LLMs) to enable unstructured data analytics. In particular, we propose a new Universal Query Engine (UQE) that directly interrogates and draws insights from unstructured data collections. This engine accepts queries in a Universal Query Language (UQL), a dialect of SQL that provides full natural language flexibility in specifying conditions and operators. The new engine leverages the ability of LLMs to conduct analysis of unstructured data, while also allowing us to exploit advances in sampling and optimization techniques to achieve efficient and accurate query execution. In addition, we borrow techniques from classical compiler theory to better orchestrate the workflow between sampling methods and foundation model calls. We demonstrate the efficiency of UQE on data analytics across different modalities, including images, dialogs and reviews, across a range of useful query types, including conditional aggregation, semantic retrieval and abstraction aggregation.
SemioLLM: Evaluating Large Language Models for Diagnostic Reasoning from Unstructured Clinical Narratives in Epilepsy
University of Tübingen（蒂宾根大学）；Technical University of Munich（慕尼黑工业大学）；University Clinic Tübingen（蒂宾根大学医院）；Hertie Institute for Clinical Brain Research（赫蒂临床脑研究所）；Excellence Cluster Machine Learning, Tübingen University（蒂宾根大学机器学习卓越集群）；Hertie Institute for AI in Brain Health (Hertie AI)（赫蒂人工智能脑健康研究所）
Text to model via SysML: Automated generation of dynamical system computational models from unstructured natural language text via enhanced System Modeling Language diagrams
Department of Engineering, University of Cambridge, Trumpington Street, Cambridge, UK（剑桥大学工程系，特鲁布里奇顿街，剑桥，英国）
Health System Scale Semantic Search Across Unstructured Clinical Notes
Department of Biomedical and Health Informatics, Children’s Hospital of Philadelphia（儿童医院哲学学院生物医学与健康信息学系）；Google Cloud（谷歌云）；Department of Pediatrics, University of Pennsylvania（宾夕法尼亚大学儿科系）；Division of Neonatology, Children’s Hospital of Philadelphia（儿童医院哲学学院新生儿科）；Division of Human Genetics, Children’s Hospital of Philadelphia（儿童医院哲学学院人类遗传学部）
Navigation-GPT: A Robust and Adaptive Framework Utilizing Large Language Models for Navigation Applications
Wuhan University of Technology（武汉理工大学）；Intelligent Transportation Systems Research Center, Wuhan University of Technology（武汉理工大学智能交通系统研究中心）；Hangzhou Dianzi University（杭州电子科技大学）；Nanjing Smart Water Transport Technology Co., Ltd.（南京智慧水运科技有限公司）
Centre National de la Recherche Scientifique（法国国家科学研究中心）；CNRS-Strasbourg University（法国国家科学研究中心-斯特拉斯堡大学）；NTNU Trondheim（特隆赫姆挪威科技大学）；Institute of Applied Informatics（应用信息学研究所）；University of South Bohemia Czech Republic（捷克南波希米亚大学）；Kogakkan University（皇学馆大学）；University of Applied Sciences Upper Austria（上奥地利应用科学大学）；Namics—A Merkle Company（Namics——Merkle旗下公司）
Detecting quality in large unstructured datasets requires capacities far beyond the limits of human perception and communicability and, as a result, there is an emerging trend towards increasingly complex analytic solutions in data science to cope with this problem. This new trend towards analytic complexity represents a severe challenge for the principle of parsimony or Occams Razor in science. This review article combines insight from various domains such as physics, computational science, data engineering, and cognitive science to review the specific properties of big data. Problems for det…
In and of itself, data storage has apparent business utility. But when we can convert data to information, the utility of stored data increases dramatically. It is the layering of relation atop the data mass that is the engine for such conversion. Frank relation amongst discrete objects sporadically ingested is rare, making the process of synthesizing such relation all the more challenging, but the challenge must be met if we are ever to see an equivalent business value for unstructured data as we already have with structured data. This paper describes a novel construct, referred to as a relat…
The D4M tool is used by hundreds of researchers to perform complex analytics on unstructured data. Over the past few years, the D4M toolbox has evolved to support connectivity with a variety of database engines, graph analytics in the Apache Accumulo database, and an implementation using the Julia programming language. In this article, we describe some of our latest additions to the D4M toolbox and our upcoming D4M 3.0 release.
STIndex: A Context-Aware Multi-Dimensional Spatiotemporal Information Extraction System
The University of Western Australia（西澳大利亚大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Murdoch University（莫道克大学）
Web query log data contain information useful to research; however, release of such data can re-identify the search engine users issuing the queries. These privacy concerns go far beyond removing explicitly identifying information such as name and address, since non-identifying personal data can be combined with publicly available information to pinpoint to an individual. In this work we model web query logs as unstructured transaction data and present a novel transaction anonymization technique based on clustering and generalization techniques to achieve the k-anonymity privacy. We conduct ex…
