Print This Page 
Email This Page
A complete development environment for Knowledge Base development, modification and update. This graphical interface offers object oriented editors, rules wizards, visual displays of extracted data, visual tools for debugging linguistic data and other displays to support analysis of performance.
A software component which applies a compiled Knowledge Base (KB) to execute the actual process of data extraction from input documents. An Instance is defined as the creation of a single Document Object in the AeroText Application Program Interface (API). Includes 3 industry standard API's (JAVA, C, COM), and wrappers available for XML and DAML. Supports both ASCII and Unicode.
A graphical tool that allows for deployment of AeroText by minimizing, and in some cases eliminating, the need to write any integration code. It is available with standard input/output formats such as XML and generic JDBC database insertion, providing for a simpler and quicker deployment than the more traditional API integration. A RIT specification is provided that allows programmers the flexibility of creating their own RIT modules to provide integration with unusual or unique input/output formats.
A graphical tool that will cluster a collection of documents based on the similarity of entities and concepts in the document.
The Key Editor is used to create an information store for scoring. It is an Answer Key that corresponds to a specific collection of documents. The Key is then used to score against extraction results to determine how accurately AeroText is extracting the desired data.
Out-of-the box linguistic driven rules library that contain the entity types used to extract text. There are over 50 entity types identified in the Core KB such as person, place, and organization names.
Out-of-the box Arabic rules library to extract entities from Arabic language documents.
Out-of-the box Chinese rules library to extract entities from Chinese language documents (both simplified and traditional).
Out-of-the-box Spanish rules library to extract entities from Spanish language documents.
Out-of-the-box Bahasa Indonesia rules library to extract entities from Bahasa Indonesia and Melagu language documents.
