Recent Advances in Dialogue Machine Translation

Recent years have seen a surge of interest in dialogue translation, which is a significant application task for machine translation (MT) technology. However, this has so far not been extensively explored due to its inherent characteristics including data limitation, discourse properties and personal...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Siyou Liu, Yuqi Sun, Longyue Wang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	dialogue neural machine translation discourse issue benchmark data existing approaches real-life applications Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/7052ef64d05c4805b4fefd254c1282ed
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7052ef64d05c4805b4fefd254c1282ed
record_format	dspace
spelling	oai:doaj.org-article:7052ef64d05c4805b4fefd254c1282ed2021-11-25T17:58:44ZRecent Advances in Dialogue Machine Translation10.3390/info121104842078-2489https://doaj.org/article/7052ef64d05c4805b4fefd254c1282ed2021-11-01T00:00:00Zhttps://www.mdpi.com/2078-2489/12/11/484https://doaj.org/toc/2078-2489Recent years have seen a surge of interest in dialogue translation, which is a significant application task for machine translation (MT) technology. However, this has so far not been extensively explored due to its inherent characteristics including data limitation, discourse properties and personality traits. In this article, we give the first comprehensive review of dialogue MT, including well-defined problems (e.g., 4 perspectives), collected resources (e.g., 5 language pairs and 4 sub-domains), representative approaches (e.g., architecture, discourse phenomena and personality) and useful applications (e.g., hotel-booking chat system). After systematical investigation, we also build a state-of-the-art dialogue NMT system by leveraging a breadth of established approaches such as novel architectures, popular pre-training and advanced techniques. Encouragingly, we push the state-of-the-art performance up to 62.7 BLEU points on a commonly-used benchmark by using mBART pre-training. We hope that this survey paper could significantly promote the research in dialogue MT.Siyou LiuYuqi SunLongyue WangMDPI AGarticledialogueneural machine translationdiscourse issuebenchmark dataexisting approachesreal-life applicationsInformation technologyT58.5-58.64ENInformation, Vol 12, Iss 484, p 484 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	dialogue neural machine translation discourse issue benchmark data existing approaches real-life applications Information technology T58.5-58.64
spellingShingle	dialogue neural machine translation discourse issue benchmark data existing approaches real-life applications Information technology T58.5-58.64 Siyou Liu Yuqi Sun Longyue Wang Recent Advances in Dialogue Machine Translation
description	Recent years have seen a surge of interest in dialogue translation, which is a significant application task for machine translation (MT) technology. However, this has so far not been extensively explored due to its inherent characteristics including data limitation, discourse properties and personality traits. In this article, we give the first comprehensive review of dialogue MT, including well-defined problems (e.g., 4 perspectives), collected resources (e.g., 5 language pairs and 4 sub-domains), representative approaches (e.g., architecture, discourse phenomena and personality) and useful applications (e.g., hotel-booking chat system). After systematical investigation, we also build a state-of-the-art dialogue NMT system by leveraging a breadth of established approaches such as novel architectures, popular pre-training and advanced techniques. Encouragingly, we push the state-of-the-art performance up to 62.7 BLEU points on a commonly-used benchmark by using mBART pre-training. We hope that this survey paper could significantly promote the research in dialogue MT.
format	article
author	Siyou Liu Yuqi Sun Longyue Wang
author_facet	Siyou Liu Yuqi Sun Longyue Wang
author_sort	Siyou Liu
title	Recent Advances in Dialogue Machine Translation
title_short	Recent Advances in Dialogue Machine Translation
title_full	Recent Advances in Dialogue Machine Translation
title_fullStr	Recent Advances in Dialogue Machine Translation
title_full_unstemmed	Recent Advances in Dialogue Machine Translation
title_sort	recent advances in dialogue machine translation
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/7052ef64d05c4805b4fefd254c1282ed
work_keys_str_mv	AT siyouliu recentadvancesindialoguemachinetranslation AT yuqisun recentadvancesindialoguemachinetranslation AT longyuewang recentadvancesindialoguemachinetranslation
_version_	1718411749927944192

Recent Advances in Dialogue Machine Translation

Ejemplares similares