Dans l'ère de l'information et de la connaissance, la traduction automatique (TA) devientprogressivement un outil indispensable pour transposer la signification d'un texte d'une langue source versune langue cible. La TA des noms propres (NP), en particulier, joue un rôle crucial dans ce processus,puisqu'elle permet une identification précise des personnes, des lieux, des organisations et des artefacts àtravers les langues. Malgré un grand nombre d'études et des résultats significatifs concernant lareconnaissance d'entités nommées (dont le nom propre fait partie) dans la communauté de TAL dans lemonde, il n'existe presque aucune recherche sur la traduction automatique des noms propres (TANP) pourle vietnamien. En raison des caractéristiques différentes d'écriture de NP, la translittération ou la transcription etla traduction de plusieurs de langues incluant l'anglais, le français, le russe, le chinois, etc. vers levietnamien, le TANP de ces langues vers le vietnamien est stimulant et problématique. Cette étude seconcentre sur les problèmes de TANP d’anglais vers le vietnamien et de français vers le vietnamienrésultant du moteurs courants de la TA et présente les solutions de prétraitement de ces problèmes pouraméliorer la qualité de la TA. A travers l'analyse et la classification d'erreurs de la TANP faites sur deux corpus parallèles detextes avec PN (anglais-vietnamien et français-vietnamien), nous proposons les solutions concernant deuxproblématiques importantes: (1) l'annotation de corpus, afin de préparer des bases de données pour leprétraitement et (2) la création d'un programme pour prétraiter automatiquement les corpus annotés, afinde réduire les erreurs de la TANP et d'améliorer la qualité de traduction des systèmes de TA, tels queGoogle, Vietgle, Bing et EVTran. L'efficacité de différentes méthodes d'annotation des corpus avec des NP ainsi que les tauxd'erreurs de la TANP avant et après l'application du programme de prétraitement sur les deux corpusannotés est comparés et discutés dans cette thèse. Ils prouvent que le prétraitement réduitsignificativement le taux d'erreurs de la TANP et, par la même, contribue à l'amélioration de traductionautomatique vers la langue vietnamienne. / Machine translation (MT) has increasingly become an indispensable tool for decoding themeaning of a text from a source language into a target language in our current information and knowledgeera. In particular, MT of proper names (PN) plays a crucial role in providing the specific and preciseidentification of persons, places, organizations, and artefacts through the languages. Despite a largenumber of studies and significant achievements of named entity recognition in the NLP communityaround the world, there has been almost no research on PNMT for Vietnamese language. Due to the different features of PN writing, transliteration or transcription and translation from a variety of languages including English, French, Russian, Chinese, etc. into Vietnamese, the PNMT from those languages into Vietnamese is still challenging and problematic issue. This study focuses on theproblems of English-Vietnamese and French-Vietnamese PNMT arising from current MT engines. First,it proposes a corpus-based PN classification, then a detailed PNMT error analysis to conclude with somepre-processing solutions in order to improve the MT quality. Through the analysis and classification of PNMT errors from the two English-Vietnamese and French-Vietnamese parallel corpora of texts with PNs, we propose solutions concerning two major issues:(1)corpus annotation for preparing the pre-processing databases, and (2)design of the pre-processingprogram to be used on annotated corpora to reduce the PNMT errors and enhance the quality of MTsystems, including Google, Vietgle, Bing and EVTran. The efficacy of different annotation methods of English and French corpora of PNs and the results of PNMT errors before and after using the pre-processing program on the two annotated corporaare compared and discussed in this study. They prove that the pre-processing solution reducessignificantly PNMT errors and contributes to the improvement of the MT systems’ for Vietnameselanguage.

Made available in DSpace on 2016-06-02T19:06:12Z (GMT). No. of bitstreams: 1 5932.pdf: 1110060 bytes, checksum: fe08b552e37f04451248c376cfc4454f (MD5) Previous issue date: 2014-04-10 / Universidade Federal de Minas Gerais / The project described in this document focusses on the post-editing of automatically translated texts. Machine Translation (MT) is the task of translating texts in natural language performed by a computer and it is part of the Natural Language Processing (NLP) research field, linked to the Artificial Intelligence (AI) area. Researches in MT using different approaches, such as linguistics and statistics, have advanced greatly since its beginning in the 1950 s. Nonetheless, the automatically translated texts, except when used to provide a basic understanding of a text, still need to go through post-editing to become well written in the target language. At present, the most common form of post-editing is that executed by human translators, whether they are professional translators or the users of the MT system themselves. Manual post-editing is more accurate but it is cost and time demanding and can be prohibitive when too many changes have to be made. As an attempt to advance in the state-of-the-art in MT research, mainly regarding Brazilian Portuguese, this research has as its goal verifying the effectiveness of using an Automated Post-Editing (APE) system in translations from English to Portuguese. By using a training corpus containing reference translations (good translations produced by humans) and translations produced by a phrase-based statistical MT system, machine learning techniques were applied for the APE creation. The resulting APE system is able to: (i) automatically identify MT errors and (ii) automatically correct MT errors by using previous error identification or not. The evaluation of the APE effectiveness was made through the usage of the automatic evaluation metrics BLEU and NIST, calculated for post-edited and not post-edited sentences. There was also manual verification of the sentences. Despite the limited results that were achieved due to the small size of our training corpus, we can conclude that the resulting APE improves MT quality from English to Portuguese. / O projeto de mestrado descrito neste documento tem como foco a pós-edição de textos traduzidos automaticamente. Tradução Automática (TA) é a tarefa de traduzir textos em língua natural desempenhada por um computador e faz parte da linha de pesquisa de Processamento de Línguas Naturais (PLN), vinculada à área de Inteligência Artificial (IA). As pesquisas em TA, utilizando desde abordagens linguísticas até modelos estatísticos, têm avançado muito desde seu início na década de 1950. Entretanto, os textos traduzidos automaticamente, exceto quando utilizados apenas para um entendimento geral do assunto, ainda precisam passar por pós-edição para que se tornem bem escritos na língua alvo. Atualmente, a forma mais comum de pós-edição é a executada por tradutores humanos, sejam eles profissionais ou os próprios usuários dos sistemas de TA. A pós-edição manual é mais precisa, mas traz custo e demanda tempo, especialmente quando envolve muitas alterações. Como uma tentativa para avançar o estado da arte das pesquisas em TA, principalmente envolvendo o português do Brasil, esta pesquisa visa verificar a efetividade do uso de um sistema de pós-edição automática (Automated Post-Editing ou APE) na tradução do inglês para o português. Utilizando um corpus de treinamento contendo traduções de referência (boas traduções produzidas por humanos) e traduções geradas por um sistema de TA estatística baseada em frases, técnicas de aprendizado de máquina foram aplicadas para o desenvolvimento do APE. O sistema de APE desenvolvido: (i) identifica automaticamente os erros de TA e (ii) realiza a correção automática da tradução com ou sem a identificação prévia dos erros. A avaliação foi realizada usando tanto medidas automáticas BLEU e NIST, calculadas para as sentenças sem e com a pós-edição; como analise manual. Apesar de resultados limitados pelo pequeno tamanho do corpus de treinamento, foi possível concluir que o APE desenvolvido melhora a qualidade da TA de inglês para português.

Notre constat de départ est que malgré un intérêt croissant des institutions enseignant les langues étrangères pour l’enseignement de la traduction, il n’existe à notre connaissance aucune étude portant sur la conception d’un programme de traduction professionnelle adapté à des apprenants de langues étrangères qui leur permettrait d’acquérir la compétence traductionnelle, c’est-à-dire les savoirs et savoir-faire nécessaires au traducteur en contexte professionnel. Ces institutions confondent souvent l’enseignement de la traduction et la traduction utilisée comme outil d’enseignement des langues étrangères. Le programme de traduction de l’université du Botswana ne fait pas exception, et nous proposons donc de le reconceptualiser afin qu’il réponde aux exigences de la profession. Par la mise à l’épreuve du modèle de l’analyse matricielle définitoire, outil linguistique destiné à interpréter et comparer la manière dont les langues naturelles construisent le sens, la présente thèse se propose de déceler les paramètres de l’environnement d’apprentissage sur lesquels une intervention est requise pour améliorer la qualité du programme et le rendre plus efficace. Pour ce faire, nous analyserons les erreurs de traduction commises par les étudiants qui suivent ce programme en vue d’en identifier les sources et de prendre les mesures destinées à en réduire la probabilité d’occurrence par la définition d’objectifs d’apprentissage adaptés à ce public, accompagnés des bases d’une solide assise théorique à destination de l’enseignant. / Our initial observation is that, in spite of the growing interest in teaching translation in institutions offering foreign language programmes, no study, to our knowledge, has been done on the designing of a professional translation programme appropriate for foreign language learners which could allow them to acquire translation competence, that is, knowledge and skills required by translators in a professional setting. These institutions often confuse teaching of translation and use of translation as a foreign language teaching tool. The translation programme of the University of Botswana is no exception, and we therefore propose to redesign it so that it can respond to the requirements of the profession. By putting to test the Defining Matrix Analysis model, a linguistic tool intended to interpret and compare the way natural languages construct sense, this thesis proposes to find the parameters of the learning environment on which an intervention is required in order to improve the quality and the efficiency of this programme. To achieve this goal, we are going to analyse translation errors made by students who are pursuing this translation programme with the aim of identifying their sources and taking measures destined to reduce their probability of occurrence by defining learning objectives adapted to this group of learners, accompanied by a solid theoretical basis for teachers.

Although Eduardo Mondlane University (UEM) has the longest history of BA Honours level translator and interpreter training in Mozambique, the university still lacks an effective model for the development of translation and interpreting competence in students. To address this problem, the present study seeks to find a practical model for the training of Mozambican professional translators and interpreters at BA Honours level that can guide the design of conducive curricula. The critical question the study attempts to answer is: What model for developing translation and interpreting competence could lead to an effective curriculum design that best meets the employment needs of Mozambican students? To this end, the study has been designed as action-research because this design enables better understanding and improvement of training processes (Cravo & Neves 2007). Three data collection tools are used to generate both qualitative and quantitative data from over 120 participants, namely: (i) a survey, (ii) an English translation test and (iii) a sample of archived Portuguese translations produced by former students. The survey findings suggest the need for a model whereby translators and interpreters are trained simultaneously within the same programme. Moreover, the results of macro- and micro-textual analysis show that, overall, the translation competence of former students is poor, suggesting that the current curriculum at UEM is failing to produce BA Honours translation/interpreting professionals. The proposed solution would be a curriculum based on a new integrated translation and interpreting competence development model with the following four pillars: communicative competence, general knowledge, strategic competence and service provision. / Nangona iyunivesithi iEduardo Mondlane University (UEM) inembali kwizifundo zesidanga esiphakamileyo (BA Honours) kuqeqesho lwabaguquleli neetoliki eMozambique, le yunivesithi ayikabi namzekelo unguwo nosebenzayo ekuphuhliseni izakhono zokuguqula nokutolika kubafundi bayo. Ukukhawulelana nale ngxaki olu phando lujolise ekufumaneni owona mzekelo usebenzayo onokusetyenziswa nonokuthi ube sisikhokelo kuyilo lwekharityhulam yesidanga esiphakamileyo iBA Honours esithatha iminyaka emine ekuqeqesheni abafundi babe ngabaguquleli neetoliki eziphume izandla zaseMozambique. Umbuzo ongundoqo nozanywa ukuphendulwa lolu phando ngulo: Ngowuphi umzekelo wokuphuhlisa izakhono zokuguqulela nokutolika onokukhokelela kuyilo lwekharityhulam esebenzayo nefezekisa iimfuno zengqesho zabafundi baseMozambique? Kungoko olu phando luye lwasebenzisa indlela yokuphanda ekuthiwa yi-action research eyenza kube lula ukuqonda nokuphucula iinkqubo zoqeqesho (Cravo & Neves 2007). Kuye kwasetyenziswa iindlela ezintathu zophando ukufumana ulwazi kubathathi-nxaxheba abali-120 ezizezi: (1) uvavanyo lwezimvo, (ii) uvavanyo lwenguqulelo yesicatshulwa esibhalwe ngesiNgesi kunye (iii) neenguqulelo zesiPhuthukezi ezenziwe ngabafundi bangaphambili ezigciniweyo. Iziphumo zeemvavanyo zezimvo zibonisa ukuba kufuneka kukho umzekelo onokusetyenziswa ekuqeqesheni abaguquleli neetoliki ngaxeshanye phantsi kwenkqubo enye. Ukongeza koku, iziphumo zohlalutyo lwesicatshulwa zibonise ukuba izakhono zokuguqulela zabafundi bangaphambili azikho mgangathweni, nto leyo ethetha ukuba ikharityhulam esetyenziswayo eUEM iyasilela ekukhupheni abaguquleli neetoliki ezinobuchule neziziincutshe. Isisombululo esicetyiswayo ke ngoko, sesokuba kubekho ikharityhulam ehlangeneyo eza kuphuhlisa izakhono zabaguquleli neetoliki esekelwe kwiintsika ezine ezizezi: isakhono sonxibelelwano, ulwazi jikelele, isakhono sobuchule kunye nokunikezwa kweenkonzo. / Nakuba iNyuvesi i-Eduardo Mondlane University (i-UEM) isinomlando omude kakhulu wokuqeqesha abahumushi notolika ezingeni leziqu ze-BA Honours eMozambique, le nyuvesi ayikabi nayo indlela esebenzayo yokuthuthukisa amakhono ezitshudeni kwezokuhumusha nokutolika. Ukubhekana nale nkinga lolu cwaningo kuhloswe ngalo ukuthola indlela esebenzayo yokuqeqesha ongoti babahumushi notolika baseMozambique ezingeni leziqu ze-BA Honours (iziqu zeminyaka emine) ezingahlahla indlela yokuklama uhlelo lwezifundo olungasiza kule nkinga. Umbuzo omkhulu lolu cwaningo oluzama ukuwuphendula ngothi: Iyiphi indlela yokuthuthukisa amakhono okuhumusha nokutolika engaholela ekuklanyweni kohlelo lwezifundo olungahlangabezana nezidingo zokuqasheka kwezitshudeni zaseMozambique? Ukufeza le nhloso, lolu cwaningo lusebenzisa uhlelo lokucwaninga olubizwa nge-action-research ngoba luyasiza ekuqondeni kangcono nasekuthuthukiseni inqubo yokuqeqesha (Cravo & Neves 2007). Kusetshenziswa amathuluzi amathathu okuqoqa imininingobunjalo nemininingobuningi evela kubabambiqhaza abangaphezu kwabayi-120, okuyilokhu: (i) ngohlolocwaningo (i-survey), (ii) ngesivivinyo sesihumusho sesiNgisi (iii) nangesampula lezihumusho zesiPutukezi zabafundi baphambilini. Okutholakale kulo uhlolocwaningo kuveza isidingo sendlela yokuqeqesha abahumushi notolika kanyekanye ohlelweni lokufundiswa olufanayo. Ngaphezu kwalokho, imiphumela yokuhlaziywa kwemibhalo nezimo eyabhalwa ngaphansi kwazo ibonisa ukuthi, ngokubanzi, amakhono okuhumusha abafundi baphambilini awamahle, okuyinkomba yokuthi uhlelo lwezifundo lwamanje e-UEM luyehluleka ukukhiqiza ongoti bokuhumusha nokutolika ezingeni le-BA Honours. Isixazululo esiphakanyiswayo ngesendlela entsha esuselwa ekuthuthukiseni amakhono edidiyela ukuhumusha nokutolika, enalezi zinsika ezine ezilandelayo: amakhono kwezokuxhumana, ulwazi ngokubanzi, ikhono lokusebenzisa amasu, nokuhlinzekwa kwezidingo. / Linguistics and Modern Languages / D. Phil. (Languages, Linguistics and Literature)