Corpus-Based Machine Translation

Summary

Introduction

Corpus-based machine translation (KOMA) is a project within the VINNOVA research program in language technology. The aim of the project is to develop methods and systems for machine translation of documents of a restricted text type.

The project is a joint project between The Natural Language Processing Laboratory (NLPLAB) at the Department of Computer and Information Science, Linköping UNiversity and the Department of Linguistics at Uppsala University.

Project goals:

to develop techniques and systems for lexical data generation from parallel corpora;
to develop applications that utilize translation data as an essential resource, e.g., when writing in a foreign language;
to improve methods and systems that have been under development at our departments with regard to their adaption to a given translation task;
to develop and apply methods for evaluation of machine translation systems.

KOMA
Latest update: 29 April, 2005.