Building an environment for unsupervised automatic e-mail translation
Abstract
In this paper, we present the INTERLINGUA Project: its design and current work. The goal of the project is achieving fully-automatic (no pre-edition, no post-edition) translation of e-mails in the Virtual Campus of the UOC. The problem of unsupervised machine translation of e-mails is discussed. Then we describe the strategy designed to build the system, including a multiple-level evaluation process and the building of several automatic pre-edition, post-edition and unknown-word extraction modules. And finally the work carried out so far on building such decision-taking modules is presented.
Keywords
Machine translation; e-mail translation; multilingualism; Human Language Technologies (HLT); Natural Language Processing (NLP)
Full Text:
PDF
The texts published in this publication are – unless otherwise indicated – covered by the Creative Commons Attribution-Non commercial-No derivative works 3.0 Spain licence. They may be copied, distributed and broadcast provided that the author, the publication and the institutions that publish them (IN3 Working Paper Series, IN3 and UOC) are cited. Commercial use and derivative works are not permitted. The full licence can be consulted on http://creativecommons.org/licenses/by-nc-nd/3.0/deed.en.