Natural language processing

English Norsk

FreetextEmployeePublications

This area is also called computational linguistics or natural language understanding, and is a wide area, generally separated in written and spoken language camps. We deal exclusively with written language in our group.

We have deployed technology (mainly in the scope of the Linguateca project) in the following areas:

semi-automatically deriving ontologies from written texts
making corpora available and queriable on the Web
dealing with parallel and comparable corpora for terminology and machine translation
non-obstrusive methods for studying users of Web services
query answering systems
crosslingual information retrieval

Published August 20, 2008

Ongoing project

Linguateca

Terminated projects

Squirrel (tools for corpus-based teaching of Scandinavian languages)
Overview of standards for Web-based learning and teaching (including, although not specifically, computer aided language learning)

Contact: {Diana Maria De Sousa Santos, tlf: +47 22067312, e-post: }