Go to:
Logótipo
Você está em: Start > Publications > View > Systèmes de traduction automatique et levée d'ambiguïté: étude comparée de systèmes de TABR, TAS et TAN
Publication

Systèmes de traduction automatique et levée d'ambiguïté: étude comparée de systèmes de TABR, TAS et TAN

Title
Systèmes de traduction automatique et levée d'ambiguïté: étude comparée de systèmes de TABR, TAS et TAN
Type
Chapter or Part of a Book
Year
2018
Authors
Bacquelaine, Françoise
(Author)
FLUP
View Personal Page You do not have permissions to view the institutional email. Search for Participant Publications Without AUTHENTICUS Without ORCID
Scientific classification
CORDIS: Humanities
Other information
Resumo (PT): FR: La traduction automatique (TA) est un domaine en pleine effervescence depuis l’invention de l’ordinateur. L’aventure a commencé par la traduction à base de règles (TABR) dans les années 1940-1950. La traduction automatique statistique (TAS) s’est imposée quelques décennies plus tard et la traduction automatique neuronale (TAN) a vu le jour au XXIe siècle. Cette distinction n’est pas stricte puisque la plupart des systèmes de TA sont aujourd’hui hybrides, mais l’ambiguïté reste un piège bien connu, tant dans le cadre de la traduction humaine que de la traduction automatique. Le mot anglais courant issue soulève deux types d’ambiguïté : « ambiguïté grammaticale » (nom ou verbe ?) et « ambiguïté homographique et polysémique » lorsqu’un mot a plusieurs sens dans la langue source (Hutchins 2005 : 17). Cette recherche se limite à trois sens du nom issue et à deux sens du verbe. Un échantillon de phrases comportant au moins une occurrence du mot issue dans un de ces cinq sens a été sélectionné dans le British National Corpus afin de comparer quatre systèmes de traduction automatique anglais-français : SYSTRAN (TABR, accès gratuit en ligne), Google Translate (TAS, accès gratuit en ligne), MT@EC (TAS, accès limité) et le système de TAN de LISA (Université de Montréal). Les résultats ont été comparés à un modèle de traduction humaine fondé sur des mémoires de traduction afin d’évaluer les faiblesses et les atouts de chaque système de TA, de comparer leurs performances et de proposer des possibilités d’amélioration grâce à l’hybridation des systèmes.
Abstract (EN): Machine Translation (MT) has been a lively field of research ever since the invention of the computer. Rule-Based Machine Translation (RBMT) was the first option back in the 1940s–1950s; Statistical Machine Translation (SMT) appeared a few decades later and Neural Machine Translation (NMT) in the 21st century. This distinction is not strict since most MT systems are now hybrid, but natural language ambiguity is a well-known pitfall, be it in human or machine translation. Two types of ambiguity can arise when using the rather common English word issue: “grammatical ambiguity” (noun or verb?), on the one hand, and “homographic and polysemic ambiguity (one word form with different senses in the source language)” (Hutchins 2005: 17), on the other hand. The scope of this research is limited to three senses of the noun issue (1. An important topic or problem for debate or discussion; 2. The action of supplying or distributing an item for use, sale, or official; 3. (formal or law) Children of one’s own) and two senses of the verb to issue (1. [WITH OBJECT] Supply or distribute (something) for use or sale; 2. [NO OBJECT] (issue from) Come, go, or flow out from). A sample of sentences containing at least one example of usage was selected from the British National Corpus in order to test and compare four English-French MT systems: SYSTRAN (free online RBMT), Google Translate (free online SMT), MT@EC (restricted access SMT) and free online Neural Machine Translation by LISA (University of Montreal). The outputs were compared to a human translation model based on translation memories (parallel corpora) in order to evaluate weaknesses and strengths of each system, compare the results and find out possible ways of improving MT output through hybridisation. Research results in cases like these are not just useful for theoretical linguistics but can also be used to heighten awareness in human translators and demonstrate that translators who are trained in computational linguistics can also work together with experts in artificial intelligence and machine translation.
Language: French
Type (Professor's evaluation): Scientific
Documents
File name Description Size
13_sistemes_de_traduction 377.72 KB
Related Publications

Of the same authors

Portas Fechadas? Janelas Abertas. Saídas Profissionais das Línguas Românicas (2007)
Educational Publication
Maria Luísa Malato Borralho; Françoise Bacquelaine
Traité de droit constitutionnel: constitution universelle et mondialisation des valeurs fondamentales (2010)
Book
Cunha, Paulo Ferreira da ; Françoise Bacquelaine; Natália Fernandes; Ágata Esmeriz; Sofia Saitta; François Vallançon
Para lá da tarefa: implicar os estudantes na aprendizagem de línguas estrangeiras no ensino superior (2019)
Book
Almeida, José Domingues de ; Auf der Maur Tomé, Simone ; Bacquelaine, Françoise ; Lorenzo, Mónica; Duarte, Isabel Margarida ; Hurst, Nicolas ; Kind, Anette ; Nicolás Martínez, Pilar; Rodrigues, Sónia Valente
Lily-Jane explode (2022)
Book
Wéry, Isabelle; Dias, Ana Catarina Teixeira ; Moura, Cassandra Isabelle ; Santos, Inês Sofia Lino dos ; Fonseca, Margarida Correia ; Bacquelaine, Françoise ; Malato, Maria Luísa
La constitution naturelle (2014)
Book
Cunha, Paulo Ferreira da ; Bacquelaine, Françoise

See all (35)

Of the same book

Os pronomes pessoais átonos na gramaticografia portuguesa setecentista (2018)
Chapter or Part of a Book
Ponce de León Romeo, Rogelio
O verbo explicar em enunciados de testes de avaliação do ensino básico : estudo de valores semânticos e pragmáticos (2018)
Chapter or Part of a Book
Rodrigues, Sónia Valente ; Duarte, Isabel Margarida ; Silvano, Maria da Purificação
O interjudge Agreement como forma de validação de trascrições de amostras dialetais (2018)
Chapter or Part of a Book
Veloso, João ; Martins, Pedro Tiago
Funções discursivas das construções com a partícula lá (2018)
Chapter or Part of a Book
Duarte, Isabel Margarida ; Marques, Maria Aldina

See all (12)

Recommend this page Top
Copyright 1996-2024 © Faculdade de Arquitectura da Universidade do Porto  I Terms and Conditions  I Acessibility  I Index A-Z  I Guest Book
Page created on: 2024-07-25 at 23:17:22 | Acceptable Use Policy | Data Protection Policy | Complaint Portal