Attensity, an emerging leader in data analysis software, announced the availability of Attensity Relational Extraction Server (RES) 3.0. Attensity RES is the only comprehensive product available that can extract valuable pieces of data from free-form text and combine them with structured content, allowing commercial enterprises and government organizations to see and respond to critical threats or opportunities that historically have been very difficult to analyze and detect. The new version features a number of enhancements, including broader platform support, improved security and superior performance.

Attensity RES is a popular solution among commercial and government organizations, with the latest version already in use at Whirlpool. Tom Welke, vice president and general manager for customer and appliance care at Whirlpool, said, "Attensity RES has been instrumental in helping us improve visibility across the whole Quality, Reliability and Durability (QRD) process. We now have much better insight into valuable information in warranty claims, customer feedback and field service records, which places us in an enviable position in terms of being able to proactively identify and address any potential problem areas."

Attensity RES is the fastest, most accurate solution for extracting and classifying facts, entities and events from language-rich information. Attensity RES eliminates the need for commercial enterprises and government agencies to resort to manual analysis and tagging of written documents - a process which is known to be slow, error-prone and expensive. It delivers up to 95 percent accuracy and generates analysis-ready data sets from free-form text sources up to 20,000 times faster than human analysts, with a raw text throughput of 5MB/minute on a 1GHz Intel CPU.

Unlike other data analytics solutions, which typically use a statistical approach to analyzing text and only provide a narrow (and often inaccurate) understanding of the information, Attensity RES grasps the nuances, relationships and context of everyday language. By analyzing the relationships between words, Attensity RES delivers a rich and accurate picture of the data.

Moreover, while other solutions simply associate unstructured content with a text field, Attensity RES takes that data, extracts critical information from it and then combines it with structured information. This enables commercial enterprises and government organizations to respond quickly to critical issues and events based on knowledge gleaned from virtually all of their information, not just some of it.

The new version of Attensity RES supports a broad range of operating systems including Windows, Solaris, and Red Hat Linux. Furthermore, it supports industry leading web servers and databases including WebLogic, WebSphere, Oracle, MySQL and Microsoft SQL Server. In addition, Attensity RES 3.0 offers support for multiple CPU and clustered server deployments for higher throughput, and boasts a new J2EE architecture for higher scalability and robust multi-threaded processing.

Attensity RES 3.0 also now features a SOAP API, which allows system integrators and third-party developers to easily embed it into existing enterprise applications. Moreover, it offers significantly improved security, with security-controlled access to sensitive documents, configuration libraries and extraction results.

In addition to its existing capabilities for relational fact and atomic fact extraction, the latest version of Attensity RES delivers direct entity extraction. These three options provide users with unprecedented flexibility in terms of the type of information they extract, from a high degree of granularity to a general set of information. Attensity RES 3.0 also includes improved Knowledge Engineering capabilities, allowing multiple analysts to concurrently develop Knowledge Libraries used for extracting information from native format and structured input files including PDF, RTF, Word, Excel, XML, CSV, HTML and Web Pages.

 

 

Register or login for access to this item and much more

All Information Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access