Discourse in Statistical Machine Translation

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 provide an extensive overview of the literature about statistical machine translation that can be related to discourse...

Full description

Saved in:
Bibliographic Details
Main Author: Christian Hardmeier
Format: Article
Language:English
Published: Presses universitaires de Caen 2012-12-01
Series:Discours
Subjects:
Online Access:https://journals.openedition.org/discours/8726
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832581841205329920
author Christian Hardmeier
author_facet Christian Hardmeier
author_sort Christian Hardmeier
collection DOAJ
description 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 provide an extensive overview of the literature about statistical machine translation that can be related to discourse phenomena and present a detailed investigation and discussion of existing research efforts on a particular discourse-related problem, the translation of anaphoric pronouns. Comparing different approaches to discourse in statistical machine translation allows us to identify fundamental problems and draw conclusions from an overarching perspective.
format Article
id doaj-art-2680fcc48b834a47a9e03763cc306e26
institution Kabale University
issn 1963-1723
language English
publishDate 2012-12-01
publisher Presses universitaires de Caen
record_format Article
series Discours
spelling doaj-art-2680fcc48b834a47a9e03763cc306e262025-01-30T09:52:43ZengPresses universitaires de CaenDiscours1963-17232012-12-011110.4000/discours.8726Discourse in Statistical Machine TranslationChristian HardmeierCurrent approaches to statistical machine translation assume that sentences in a text are independent, ignoring the property of connectedness present in virtually all discourse. We provide an extensive overview of the literature about statistical machine translation that can be related to discourse phenomena and present a detailed investigation and discussion of existing research efforts on a particular discourse-related problem, the translation of anaphoric pronouns. Comparing different approaches to discourse in statistical machine translation allows us to identify fundamental problems and draw conclusions from an overarching perspective.https://journals.openedition.org/discours/8726discoursestatistical machine translationpronominal anaphorasurvey
spellingShingle Christian Hardmeier
Discourse in Statistical Machine Translation
Discours
discourse
statistical machine translation
pronominal anaphora
survey
title Discourse in Statistical Machine Translation
title_full Discourse in Statistical Machine Translation
title_fullStr Discourse in Statistical Machine Translation
title_full_unstemmed Discourse in Statistical Machine Translation
title_short Discourse in Statistical Machine Translation
title_sort discourse in statistical machine translation
topic discourse
statistical machine translation
pronominal anaphora
survey
url https://journals.openedition.org/discours/8726
work_keys_str_mv AT christianhardmeier discourseinstatisticalmachinetranslation