La traduction multilingue : analyse d'une prouesse technologique

Neural machine translation (NMT) systems have made tangible progress in recent years, making them usable for an increasing number of domains and language pairs. The development of neural systems is based on machine learning algorithms and requires large electronic corpora of parallel texts, aligned...

Full description

Bibliographic Details
Main Author: François Yvon
Format: Article
Language:English
Published: University of Bologna 2023-12-01
Series:MediAzioni
Subjects:
Online Access:https://mediazioni.unibo.it/article/view/18785
_version_ 1797373577355329536
author François Yvon
author_facet François Yvon
author_sort François Yvon
collection DOAJ
description Neural machine translation (NMT) systems have made tangible progress in recent years, making them usable for an increasing number of domains and language pairs. The development of neural systems is based on machine learning algorithms and requires large electronic corpora of parallel texts, aligned at the sentence level. Such resources however only exist for a small number of language pairs and domains. To overcome this problem, a recent proposal is to develop so-called “multilingual” translation systems. These developments have been driven in particular by major Internet players, who need to develop automatic language processing tools for as many languages as possible. The main characteristic of these systems is to process multiple languages, both on the source and target sides, with a single translation engine. In this paper, we present the general principles underlying these systems and the innovations that have made them possible, before discussing their main strengths and weaknesses.
first_indexed 2024-03-08T18:52:29Z
format Article
id doaj.art-e2e244e52c214e5c9d1fd746022b1a8e
institution Directory Open Access Journal
issn 1974-4382
language English
last_indexed 2024-03-08T18:52:29Z
publishDate 2023-12-01
publisher University of Bologna
record_format Article
series MediAzioni
spelling doaj.art-e2e244e52c214e5c9d1fd746022b1a8e2023-12-28T16:33:05ZengUniversity of BolognaMediAzioni1974-43822023-12-0139A17A3410.6092/issn.1974-4382/1878517144La traduction multilingue : analyse d'une prouesse technologiqueFrançois Yvon0CNRS PARISNeural machine translation (NMT) systems have made tangible progress in recent years, making them usable for an increasing number of domains and language pairs. The development of neural systems is based on machine learning algorithms and requires large electronic corpora of parallel texts, aligned at the sentence level. Such resources however only exist for a small number of language pairs and domains. To overcome this problem, a recent proposal is to develop so-called “multilingual” translation systems. These developments have been driven in particular by major Internet players, who need to develop automatic language processing tools for as many languages as possible. The main characteristic of these systems is to process multiple languages, both on the source and target sides, with a single translation engine. In this paper, we present the general principles underlying these systems and the innovations that have made them possible, before discussing their main strengths and weaknesses.https://mediazioni.unibo.it/article/view/18785neural machine translationmultilingual machine translationcross-lingual transferneural interlingua
spellingShingle François Yvon
La traduction multilingue : analyse d'une prouesse technologique
MediAzioni
neural machine translation
multilingual machine translation
cross-lingual transfer
neural interlingua
title La traduction multilingue : analyse d'une prouesse technologique
title_full La traduction multilingue : analyse d'une prouesse technologique
title_fullStr La traduction multilingue : analyse d'une prouesse technologique
title_full_unstemmed La traduction multilingue : analyse d'une prouesse technologique
title_short La traduction multilingue : analyse d'une prouesse technologique
title_sort la traduction multilingue analyse d une prouesse technologique
topic neural machine translation
multilingual machine translation
cross-lingual transfer
neural interlingua
url https://mediazioni.unibo.it/article/view/18785
work_keys_str_mv AT francoisyvon latraductionmultilingueanalyseduneprouessetechnologique