Statistical Machine Translation Support Improves Human Adjective Translation
G. Kremer, M. Hartung, S. Padó, and S. Riezler. Crossroads between Contrastive Linguistics, Translation Studies and Machine Translation: TC3 II, Language Science Press, (2017)
Abstract
In this paper we present a study in computer-assisted translation, investigating
whether non-professional translators can profit directly from automatically constructed bilingual phrase pairs. Our support is based on state-of-the-art statistical
machine translation (smt), consisting of a phrase table that is generated from large
parallel corpora, and a large monolingual language model. In our experiment, human translators were asked to translate adjective–noun pairs in context in the presence of suggestions created by the smt model. Our results show that smt support
results in an acceptable slowdown in translation time while significantly improving translation quality.
%0 Book Section
%1 kremer11:_phras_table_suppor_for_human_trans
%A Kremer, Gerhard
%A Hartung, Matthias
%A Padó, Sebastian
%A Riezler, Stefan
%B Crossroads between Contrastive Linguistics, Translation Studies and Machine Translation: TC3 II
%D 2017
%E Culo, Oliver
%E Hansen-Schirra, Silvia
%I Language Science Press
%K article imported myown
%P 121-152
%T Statistical Machine Translation Support Improves Human Adjective Translation
%U http://dx.doi.org/10.5281/zenodo.1019697
%X In this paper we present a study in computer-assisted translation, investigating
whether non-professional translators can profit directly from automatically constructed bilingual phrase pairs. Our support is based on state-of-the-art statistical
machine translation (smt), consisting of a phrase table that is generated from large
parallel corpora, and a large monolingual language model. In our experiment, human translators were asked to translate adjective–noun pairs in context in the presence of suggestions created by the smt model. Our results show that smt support
results in an acceptable slowdown in translation time while significantly improving translation quality.
@incollection{kremer11:_phras_table_suppor_for_human_trans,
abstract = {In this paper we present a study in computer-assisted translation, investigating
whether non-professional translators can profit directly from automatically constructed bilingual phrase pairs. Our support is based on state-of-the-art statistical
machine translation (smt), consisting of a phrase table that is generated from large
parallel corpora, and a large monolingual language model. In our experiment, human translators were asked to translate adjective–noun pairs in context in the presence of suggestions created by the smt model. Our results show that smt support
results in an acceptable slowdown in translation time while significantly improving translation quality.},
added-at = {2017-04-03T19:29:27.000+0200},
author = {Kremer, Gerhard and Hartung, Matthias and Pad\'o, Sebastian and Riezler, Stefan},
biburl = {https://puma.ub.uni-stuttgart.de/bibtex/24f732d45485b16aeac075620be310367/sp},
booktitle = {Crossroads between Contrastive Linguistics, Translation Studies and Machine Translation: TC3 II},
editor = {Culo, Oliver and Hansen-Schirra, Silvia},
interhash = {8d4199eb225ca7bfa6224aed0cc98c5c},
intrahash = {4f732d45485b16aeac075620be310367},
keywords = {article imported myown},
pages = {121-152},
publisher = {Language Science Press},
timestamp = {2018-02-20T12:04:14.000+0100},
title = {Statistical Machine Translation Support Improves Human Adjective Translation},
type = {Publication},
url = {http://dx.doi.org/10.5281/zenodo.1019697},
year = 2017
}