We investigate the use of extended context in attention-based neural machine translation.
We base our experiments on translated movie subtitles and discuss the effect of increasing …

Abstract Hardmeier, C. 2014. Discourse in Statistical Machine Translation. Studia Linguistica
Upsaliensia 15. 185 pp. Uppsala: Acta Universitatis Upsaliensis. ISBN 978-91-554-8963-2 …

Recently a number of approaches have been proposed to improve translation performance
for document-level neural machine translation (NMT). However, few are focusing on the …

Cross-sentence context can provide valuable information in Machine Translation and is
critical for translation of anaphoric pronouns and for providing consistent translations. In this …

We describe Docent, an open-source decoder for statistical machine translation that breaks
with the usual sentence-bysentence paradigm and translates complete documents as units …

SMT typically models translation at the sentence level, ignoring wider document context.
Does this hurt the consistency of translated documents? Using a phrase-based SMT system …

Current approaches to statistical machine translation assume that sentences in a text are
independent, ignoring the property of connectedness present in virtually all discourse. We …

Lexical chains provide a representation of the lexical cohesion structure of a text. In this
paper, we propose two lexical chain based cohesion models to incorporate lexical cohesion …

In this article, we explore the potential of using sentence-level discourse structure for
machine translation evaluation. We first design discourse-aware similarity measures, which …

A number of approaches have been taken to improve lexical consistency in Statistical
Machine Translation. However, little has been written on the subject of where and when to …