Information Today, Inc. Corporate Site KMWorld CRM Media Streaming Media Faulkner Speech Technology Unisphere/DBTA
PRIVACY/COOKIES POLICY
Other ITI Websites
American Library Directory Boardwalk Empire Database Trends and Applications DestinationCRM Faulkner Information Services Fulltext Sources Online InfoToday Europe KMWorld Literary Market Place Plexus Publishing Smart Customer Service Speech Technology Streaming Media Streaming Media Europe Streaming Media Producer Unisphere Research



News & Events > NewsBreaks
Back Index Forward
Threads bluesky LinkedIn FaceBook Instagram RSS Feed
 



ClearForest Upgrades Its Flagship Intelligence Product
by
Posted On October 27, 2003
ClearForest Corp. has announced the availability of ClearForest 5.0. The company offers products that read vast amounts of structured and unstructured text; extract relevant information that's specific to users' requirements; and provide visual, interactive, and textual executive summaries. The new 5.0 release adds relationship-analysis tools, industry-specific solution modules, and enhanced database scalability. ClearForest can now tag and analyze Arabic and Hebrew in addition to Western European languages.

Federal agencies as well as pharmaceutical/biotech, publishing, and other research-intensive companies use ClearForest's data-mining solutions to gain access to the critical "knowledge nuggets" buried in their unstructured data. ClearForest is not a search engine, but it can work with them. Its ClearTags platform produces standard tagged XML that can be searched with other software, such as Endeca. Barak Pridor, ClearForest's CEO, calls it a business intelligence solution that provides for the discovery of facts, patterns, trends, and relationships that would otherwise be hidden within an organization's unstructured data. He said: "If you know what you're looking for, use a search tool. If you don't know what you're looking for, use a discovery tool."

Pridor said that the two primary markets for ClearForest are the defense/intelligence community and the publishing field. The company is building into the life sciences and manufacturing markets as well. It had been targeting customers in the financial services space, but that market dried up after 9/11. Since then, the defense/intelligence and homeland security needs of government agencies have given the company a huge boost. The use of ClearForest technology by government agencies is actually pulling along the commercial market.

The FBI joined as a customer in January 2003 and uses ClearForest on 300 analysts' desktops for its counter-terrorism system. A major stock exchange uses ClearForest for a fraud and insider-trading-detection application. Pridor said that the company would be announcing in the next month its first major pharmaceutical company customer.

A major change with the 5.0 release is the uncoupling of ClearForest's platform and application components. Previously, they had been inseparable. The ClearTags Intelligent-Tagging platform employs semantic, statistical, and structural analysis to classify documents and discover pertinent buried entities, events, facts, and relationships, thus producing richly tagged XML. The ClearResearch application then automatically integrates tagged content from multiple sources and delivers visual, interactive summaries. Or, as Pridor says, it "structures the unstructured."

A new Link Analysis query automatically organizes links between entities that are not present in individual documents. The results can give new insight into an organization's data by interpreting the relevant interconnections between disparate bits of information. In other words, Link Analysis finds indirect but important connections. Pridor calls this "connecting the dots." Users can then browse through the links and click to see the supporting documents. For example, they could see the documents that support the discovered relationship between a terrorist group and a charitable organization.

A new Fact Viewer allows for the search and retrieval of events and relationships without the constraint of explicit keywords. A financial analyst could ask for a list of "all biotech companies that merged or were acquired in the past 6 months," even though the words "merged," "acquired," or "acquisition" might not appear in the source text.

The ClearForest product has added the four new Discovery Modules that provide cost-saving, out-of-the-box text patterns and relationships for applications in life sciences, counterintelligence, intellectual property, and financial services. The expertise in the modules guides the automatic tagging and discovery of the most relevant textual elements to each specific domain or industry. Organizations can incorporate their own expertise as well.

Starting operations in 1998 as Instinct Software, ClearForest was founded by Ronen Feldman, an expert in text-mining, and Yonatan Aumann, an expert in the field of algorithm design and analysis. Their goal was "drastically reducing the time needed to obtain knowledge from information and to improve its relevance and quality." As the company's name signifies, it allows users to obtain a "clear" view of the information "forest."

ClearForest's customers include Thomson Financial, Elsevier Science, Dow Chemical, and the FBI. The company is headquartered in New York, with R&D facilities in Israel and sales offices in Washington, D.C. It currently has 72 employees. ClearForest recently completed its third major round of financing, led by Greylock.


Paula J. Hane is a freelance writer and editor covering the library and information industries. She was formerly Information Today, Inc.’s news bureau chief and editor of NewsBreaks.


Comments Add A Comment

              Back to top