TERAGRAM'S ENTITIES AND EVENTS EXTRACTION SOFTWARE MINES TENS OF MILLIONS OF TOPICS PER YEAR FOR READERS OF MAJOR NEWS SITES

Cambridge, Mass. - Septemeber 17, 2007 - Teragram, the leading provider of multilingual natural language processing technologies, announced today that its Entities and Events Extraction technology is responsible for the categorization, classification, entities extraction and quick delivery of millions of news articles per month. With most of the top news properties in the USA utilizing the software, including the New York Times, Associated Press, Forbes.com, Boston.com and CNN.com, this equates to tens of millions of accurately extracted and delivered news items per year.

Few organizations require the extraction and comprehensive analysis of information as urgently as the major news outlets. Readers and subscribers to these Websites benefit from Teragram's Entities and Events Extraction software every time they search, browse news by subjects, subscribe to e-mail alerts, or receive specialized content delivered to their desktops. Teragram's software enables news organizations to perform effective text analytics on documents to then extract and deliver information on people, celebrities, organization, places, topics, events, concepts and issues, providing end users with accurate and timely news on the topics they care about most.

Teragram's extraction technology is one of the driving forces behind the customization by readers of online news content across the Internet. For example, readers may browse news content by topics or entities such as people, subjects, organization and places. They may also elect to receive Teragram-extracted entities, such as a company, event or a person's name, through e-mail alerts. Additionally, newswires can deliver more relevant content, customized by location and subject matter, to subscriber news organizations. And, online news portals have the ability to simplify their end user search experience by using a system of taxonomies to break down news by categories, subjects and entities, (organization, people, places, etc.) finding connections between key pieces of news. Behind each of these powerful benefits is Teragram's entities and events extraction capability.

Entities and Events Extractor -- A Collaborative Tool
Teragram's Entities and Events Extractor software can be used by teams of people, enabling specialists in news organizations to collaboratively create, manage and implement information extraction in real-time. This team approach and process greatly increases the efficiency and accuracy of information retrieval for end-users worldwide.

By incorporating collaborative features, Teragram enables more than one news editor to modify the rules for extraction across an organization. This feature allows users to establish rules simultaneously, yet only within their areas of specialization, such as bureaus or departments, similarly to the way outlets break down sections of their newspapers, magazine or Websites. For example, if a sports editor wishes to change extraction categories, that editor may do so instantaneously without affecting the categories established by the entertainment, financial, world news or other such editors' preferences.

How it Works
The Teragram Entities and Events Extraction automatically detects and extracts entities, concepts and events from text and documents. Entities and concepts such as people's and company's names, publicly traded businesses, titles and positions, and geographical locations are among many of the concepts that are automatically extracted from text. These concepts can be easily customized for specific domains, organizations and uses. Entities and Events Extraction is available as a stand-alone enterprise system or an OEM product, to enhance other applications such as CRM Systems, Knowledge Bases and Search.

In addition to identifying concepts in text, Teragram Entities and Events Extraction can also output information associated with the extracted concepts. For example, Teragram Concept Extraction not only extracts publicly traded companies mentioned in documents but also outputs their ticker symbol and the stock market where they are listed. The extraction software can also use Teragram's Automatic XML Marker technology to enable the automatic production of XML tags associated with concepts extracted.

Technorati Tags: Text analytics, search, and collaborative tools

About Teragram^SM
Teragram is the market leader in mobile and multilingual natural language processing technologies that use the meaning of text to distill relevant information from vast amounts of data. Founded in 1997 by innovators in the field of computational linguistics, Teragram alone offers the speed, accuracy and global language support that customers and partners demand to retrieve and organize growing volumes of digital information. Teragram helps customers perform more efficient searches and better organize information in more than 30 languages, enabling them to reach new markets and make better decisions. Teragram serves customers across the publishing, pharmaceutical, telecommunications and financial industries, including AOL, Ariba, Ask Jeeves, Associated Press, CNN, Factiva, EBSCO Publishing, Ebay, FAST Search & Transfer, Forbes.com, InfoSpace, Naval Post Graduate School, NYTimes Digital, OneSource, Reed Business Information, Ricoh, Sony, Verity, WashingtonPost.com, Wolters Kluwer, the World Bank and Yahoo. For more information please contact 1-617-576-6800 or visit http://www.teragram.com/info.