SBIR Phase II: Xtractica - A System for Extracting Coherent Data from Documents

这个小型企业创新研究第二阶段项目将实施一个软件系统，允许领域专家指定程序，将来自各种文档源的非结构化或部分结构化数据转换为结构化、连贯和易于使用的信息。该系统将由一套紧密集成的句法和语义驱动的数据提取技术组成，这些技术通过图形用户界面进行管理。其目标将是检索为人类可理解而创建的信息，并与其合作创建能够支持自动决策和交易的知识。该系统将使用户能够迅速将数据结构化为知识，这些用户了解自己的应用领域，但不一定接受过计算技术专家的培训。第二阶段的实施工作将以第一阶段可行性研究的结果为基础，以生产一个功能齐全的系统。第三阶段将使具有不同商业利益的客户可以在商业上使用该系统，包括内容聚合、电子采购、企业资源规划和供应链管理供应商。

This Small Business Innovation Research Phase II project will implement a software system that allows domain experts to specify programs that transform unstructured or partially structured data from a variety of document sources, such as World Wide Web sites, PDF files, and text into structured, coherent, and readily usable information. The system will consist of a set of tightly integrated syntactic and semantics-driven data extraction technologies that are managed from a graphical user interface. The goal will be to retrieve information that was created for human understandability, and work with it to create knowledge that can support automated decision-making and transactions. The system will empower users, who are knowledgeable about their application domains but are not necessarily trained as computing technologists, to rapidly structure data into knowledge. The Phase II implementation effort will build upon the results from the Phase I feasibility study to produce a fully functional system.Phase III will make the system commercially available to clients with diverse business interests including content aggregation, e-procurement, ERP, and supply chain management vendors.