Skip to main content

Software  > Globalization > 

Globalize your On Demand Business

Linguini is a vector-space based categorizer used for high-precision language identification in IBM Intelligent Miner for Text.

Executive overview

"Given the vast and still-growing availability of electronic documents from around the world, it is increasingly important that managers of the information systems on which they are stored handle them appropriately. They should sort or tag the documents so that users can readily access those that are of most interest and use to them, which in our case means delivering only those in a language they understand."

-- John M. Prager
IBM Watson Research Center

Continue to "Welcome to Linguini"

Further reading

Items marked with a PDF icon require Adobe Acrobat Reader.

Reading between the lines
PDF LinkAnti-serendipity: Finding Useless Documents and Similar Documents
Jiri Navratil - Publications
EIP Information Mining in a Nutshell
Outside IBM LinkLanguage identification tools
Outside IBM LinkTextcat Language Guesser Demo
Outside IBM LinkDomainStats.com site

E-mail us
Easy ways to get the answers you need.
E-mail us