METIS-II: Low Resource Machine Translation

METIS-II: Low Resource Machine Translation

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 monolingu...

Full description

Saved in:
Bibliographic Details
Published in:Machine translation Vol. 22; no. 1/2; pp. 67 - 99
Main Authors: Carl, Michael, Melero, Maite, Badia, Toni, Vandeghinste, Vincent, Dirix, Peter, Schuurman, Ineke, Markantonatou, Stella, Sofianopoulos, Sokratis, Vassiliou, Marina, Yannoutsou, Olga
Format: Journal Article
Language:English
Published: Dordrecht Springer 01-03-2008
Springer Netherlands
Subjects:
Applied linguistics
Artificial Intelligence
Computational Linguistics
Computer Science
Dictionaries
Grammatical clauses
Language
Language translation
Linguistics
Machine translation
Natural Language Processing (NLP)
Phrases
Sentences
Translation
Verbs
Words
Statistical MT
Shallow linguistic processing for MT
Low resource MT
Pattern-based MT
Machine translation
Pattern-based MT, Shallow linguistic processing for MT
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0922-6567
1573-0573
DOI:10.1007/s10590-008-9048-z