Colloque

IT: opening doors to minor languages

Cristina Borrell

Antoni Oliver

Membre a labase

Cristina Borrell

Résumé du colloque

Multilingualism is a reality in the 21st century and Information Technology reveal as a powerful way to cope with the challenges its treatment implies. Our team has developed a set of tools aiming to automatically extract terminology. The extractor is multiplatform and can be adapted to the users' needs. One of its most useful applications is the elaboration of glossaries, both monolingual and multilingual, based on a set of documents. This system automatically extracts the term candidates from the texts introduced by the user. It can also create terminology databases from a set of documents of a specific field, allowing the user to automatically obtain a list of multilingual lexical units. Finally it can propose translation candidates, assisting translators when translating specialized documents. At the end of the extraction, a linguist has to review the list of lexical units to verify the result. This is so because the extractor works in a statistical way. However, its usage saves time and effort to the translator, who only has to check if the candidate is correct or not. The set of tools has been programmed in Perl, with a totally modular and easily adaptable development. It has been published under license GNU/GPL, reason why it is freely distributed. IT is a key factor to keep in mind when thinking of promoting multilingualism, especially for those languages with few economical resources.