METIS-II: low resource machine translation

  • Authors:
  • Michael Carl;Maite Melero;Toni Badia;Vincent Vandeghinste;Peter Dirix;Ineke Schuurman;Stella Markantonatou;Sokratis Sofianopoulos;Marina Vassiliou;Olga Yannoutsou

  • Affiliations:
  • Institut für Angewandte Informationsforschung, Saarbrucken, Germany 66121;GLiCom (Fundaci Barcelona Media-UPF), Barcelona, Spain 08002;GLiCom (Fundaci Barcelona Media-UPF), Barcelona, Spain 08002;KU Leuven-Centrum voor Computerlinguïstiek, Leuven, Belgium 3000;KU Leuven-Centrum voor Computerlinguïstiek, Leuven, Belgium 3000;KU Leuven-Centrum voor Computerlinguïstiek, Leuven, Belgium 3000;Institute for Language and Speech Processing, Athens, Greece 15125;Institute for Language and Speech Processing, Athens, Greece 15125;Institute for Language and Speech Processing, Athens, Greece 15125;Institute for Language and Speech Processing, Athens, Greece 15125

  • Venue:
  • Machine Translation
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

METIS-II was an EU-FET MT project running from October 2004 to September 2007, which aimed at translating free text input without resorting to parallel corpora. The idea was to use "basic" linguistic tools and representations and to link them with patterns and statistics from the monolingual target-language corpus. The METIS-II project has four partners, translating from their "home" languages Greek, Dutch, German, and Spanish into English. The paper outlines the basic ideas of the project, their implementation, the resources used, and the results obtained. It also gives examples of how METIS-II has continued beyond its lifetime and the original scope of the project. On the basis of the results and experiences obtained, we believe that the approach is promising and offers the potential for development in various directions.