New ABBYY InfoExtractor SDK, Smart Classifier for Automating Business Document Processes
ABBYY, provider of technologies for automating information processes, has launched two new language-based solutions that it says will enabling businesses to better understand and act on complex, unstructured information. Based on ABBYY’s newly announced Compreno natural-language processing (NLP) technology, the new ABBYY InfoExtractor SDK and ABBYY Smart Classifier are designed to enable development of next-generation “smart business” document-process applications.
ABBYY InfoExtractor is a Software Development Kit (SDK) that enables enterprises, as well as software developers, to automatically identify and extract entities and relationships from complex text documents. It uses facts and events to reconstruct “story lines” in documents for enhanced user insight. It automates the processing of complex, business-critical documents, and provides information transparency to reduce risk and optimize case and asset management. ABBYY InfoExtractor’s NLP is designed to be enhanced with domain-specific ontologies to accurately extract complicated or industry-specific terms, clauses, and facts. It supports various file formats, including Microsoft Word and XML, PDF, Tiff, JPEG and other graphic formats.
For more information on InfoExtractor, visit ABBYY here.
According to ABBYY, Smart Classifier is a classification-application module that enables enterprises and software developers to overcome implementation and usage complexities that have hindered widespread adoption of classification technology. It’s said to combine robust text- and semantic-based classification algorithms, an intuitive, graphical Model Editor interface, and automatic optimization algorithms to make classification dependable for information governance, email and content management, data migration. and other critical processes. The Model Editor workflow interface allows IT and business users to easily create, evaluate, and refine taxonomies and classification models, and adapts to organizations’ needs by providing “the most accurate categorizations possible.” With REST APIs and support for 39 languages, including English, ABBYY says Smart Classifier delivers highly accurate classification to mitigate risk, ensure defensible retention policies, and organize large repositories to enhance information retrieval in organizations.
For more information on Smart Classifier, visit ABBYY here.
- February 2015: ABBYY’s Updated PDF Transformer+ Provides Faster Printing, Start-Up, and More
- December 2014: ABBYY Europe Partnering with Fujitsu to Expand Document-Capture Solutions
- July 2014: ABBYY Releases Next Generation of FineReader Online with New Document-Conversion Features
- May 2014: Next-Generation ABBYY Recognition Server Features Extended PDF Capabilities, Direct SharePoint Integration
- April 2014: Next-Generation ABBYY FineReader 12 Corporate OCR Software with Upgrades