OrcaTec LLC

Information Retrieval Toolkit Version 2.0 for Electronic Discovery

Adds Near Duplicate Clustering and Concept Search to Applications

Ojai, CA (January 16, 2008) — OrcaTec LLC, a leading provider of information retrieval software and consulting for electronic discovery, today announced the release of Version 2.0 of its Information Retrieval Toolkit. The Toolkit, distributed as a software appliance, allows eDiscovery service providers to enhance their product offering with concept search, near-duplicate clustering, language identification, and an interesting-phrase finder.

In Version 2.0, data ingest rates as high as 2 million documents per day can be achieved. The toolkit enables service providers to meet the demands of high processing rates and effective information management that their eDiscovery clients require.

“We are very excited to be able to offer groundbreaking software to electronic discovery service providers,” said Herbert L. Roitblat, Ph.D., Principal of OrcaTec LLC. “Concept search and near-duplicate clustering have been at the forefront of efforts to reduce the burden of electronic discovery. This release brings these capabilities within reach of every eDiscovery Service Provider.”

“A high proportion of documents in a typical eDiscovery case can be near duplicates,” said Brian Golbère, Principal of OrcaTec LLC. “Grouping these similar documents together can save reviewers a lot of time and improve their accuracy.”

About the OrcaTec Information Retrieval Toolkit

The patent pending OrcaTec Information Retrieval Toolkit is designed to be integrated into systems for legal discovery, enterprise search, business intelligence, text data mining, email archiving, knowledge management, and other applications—anywhere finding is more important than searching.

OrcaTec Concept Searching learns the meaning of words from the documents that it reads, without having to rely on domain experts. It provides more accurate results than can be obtained with ordinary search engines and it is far easier to set up and maintain than systems that rely on taxonomies or ontologies. The Toolkit also includes the full complement of Boolean and proximity searching users expect.

The Toolkit is based on language modeling, which is the process of analyzing the patterns of language usage in a text and using these patterns to organize and retrieve it. The Toolkit has a very powerful, but very easy to use REST-based API.

The Toolkit is distributed as an rPath software appliance, making it ultra-simple to install and maintain. It is licensed on an annual subscription, rather than per document or per seat basis.

About OrcaTec LLC

OrcaTec LLC delivers next generation software for information management and analysis tools for incorporation in third party applications. OrcaTec principals have long been leaders in electronic discovery introducing a broad range of innovations to the process of eDiscovery. OrcaTec also offers a full range of consulting services in electronic discovery, information retrieval, and information analysis. OrcaTec’s international client base includes electronic discovery service providers, government agencies, and companies in information management.

Media Relations Contacts:

Herbert Roitblat, Ph.D.
805-212-8265
herb@orcatec.com

Jan 8, 11:44 AM