This chapter contains sections titled: Introduction, Machine Translation and Linguistics, Machine Translation and Computer Science, The Statistical Defense, The Sorcerer's-Apprentice Defense, The Translator's Amanuensis, Text Editing, Translation Aids, Machine Translation

The Proper Place of Men and Machines in Language Translation

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Rapports d’activité 2010

Discussions on the teaching of machine translation (MT) have usually remained confined to translation technology pedagogy. Syllabus design, models for competence development, methodologies and evaluation procedures in this area have benefited from advances in translation pedagogy, but findings relating to the teaching of MT have been slow to be implemented in the translation classroom. Numerous studies have reflected translators’ perspectives on MT, including those of professional associations, employers, and institutional organizations. Students’ perspectives have also been collected, but the voice of the translation instructors is yet to be heard. A number of questions arise: What do translator educators think of MT? Would they be willing to use it in the translation classroom? If so, how and to what purpose? To answer these and related questions, we present the results of a qualitative study conducted with a group of translation educators at Universitat de València (University of Valencia, Spain) in the context of a broader research project. We specifically investigated their beliefs and perspectives towards the introduction of MT into the translation classroom. We used open-ended questions to collect qualitative data, and subsequently analysed responses within the framework of Grounded Theory. Findings provide valuable insights for discussion on the following topics: MT literacy, the blurring of MT key concepts and categorizations, the effect of MT on the development of translation competences, agency in MT reaching a stage where there is no longer a place for the human translator, and the eventual eclipse of the translator. 

The role of machine translation in translation education: A thematic analysis of translator educators’ beliefs

Cette these a pour objet le traitement automatique du phenomene elliptique. A la croisee de plusieurs disciplines – linguistique theorique, linguistique de corpus, linguistique outillee et traductologie –, elle s’inscrit dans une demarche experimentale en poursuivant deux objectifs essentiels. Il s’agit tout d’abord de verifier la possibilite de detecter automatiquement le phenomene elliptique en anglais pour explorer ensuite les procedures facilitant sa traduction automatique de l’anglais vers le francais. La detection automatique repose sur des analyses morphosyntaxiques qui paraissent suffisantes a la detection automatique de certaines categories d’ellipse, puisqu’en decomposant le phenomene, elles permettent de l’identifier parmi d’autres. Un corpus parallele et multi-genres, collecte et concu pour repondre aux hypotheses de recherche, est utilise. Afin d’elaborer des patrons de detection et exploiter le corpus, cette recherche utilise les outils CoreNLP developpes a l’universite de Stanford (USA) et met en lumiere leurs limites lorsqu’ils sont confrontes a l’ellipse. Les resultats obtenus s’articulent autour du lien etabli entre la detection et la traduction automatiques du phenomene elliptique, facteur determinant dans la comprehension des erreurs de traduction generees lors de son traitement automatique.

https://tel.archives-ouvertes.fr/tel-02526670/document

La détection et la traduction automatiques de l'ellipse : enjeux théoriques et pratiques

Traditionally, human–machine interaction to reach an improved machine translation (MT) output takes place ex-post and consists of correcting this output. In this work, we investigate other modes of intervention in the MT process. We propose a Pre-Edition protocol that involves: (a) the detection of MT translation difficulties; (b) the resolution of those difficulties by a human translator, who provides their translations (pre-translation); and (c) the integration of the obtained information prior to the automatic translation. This approach can meet individual interaction preferences of certain translators and can be particularly useful for production environments, where more control over output quality is needed. Early resolution of translation difficulties can prevent downstream errors, thus improving the final translation quality “for free”. We show that translation difficulty can be reliably predicted for English for various source units. We demonstrate that the pre-translation information can be successfully exploited by an MT system and that the indirect effects are genuine, accounting for around 16% of the total improvement. We also provide a study of the human effort involved in the resolution process.

/pdf/reassessing-the-proper-place-of-man-and-machine-in-42cpo68ye8.pdf

Reassessing the proper place of man and machine in translation: a pre-translation scenario

Statistical Machine Translation (SMT) systems integrate various models that exploit all available features during decoding to produce t he best possible translation hypo- theses. Correctly translating polysemous words, such as the French word avocat into English (lawyer or avocado) requires integrating complex models. Such translation lexical ambiguities, however, depend on the language pair considered. If one knows, for instance, that avocat was translated into Spanish as aguacate, then translating it into English is no longer ambiguous (avocado). Thus, in this example, the knowledge of the Spanish translation allows to reinforce the choice of the appropriate English word for the French! English system. In this article, we present an approach in which documents available in several languages are used to reinforce the lexical choices made by a SMT system. In particular, we show that gains can be obtained on several metrics when using auxiliary translations produced by human translators. Mots-cles : Traduction automatique statistique, desambiguisation lexicale, reevaluation de listes d'hypotheses.

http://www.quaero.org/media/files/bibliographie/limsi_qpr6_crego_taln09-multisource.pdf

Plusieurs langues (bien choisies) valent mieux qu'une : traduction statistique multi-source par renforcement lexical

We introduce a generic framework in Statistical Machine Translation (SMT) in which lexical hypotheses, in the form of a target language model local to the input sentence, are used to guide the search for the best translation, thus performing a lexical microadaptation. An in- stantiation of this framework is presented and evaluated on three language pairs, where these auxiliary hypotheses are derived through triangulation via an auxiliairy language. Our first ex- periments consider nine auxiliary languages, allowing us to measure their individual contribu- tion. We then combine all their hypotheses through a decoding by consensus. Our experiments show that SMT systems can be improved by automatically produced auxiliary hypotheses.

Micro-adaptation lexicale en traduction automatique statistique 1

In this article, we show how using both on-demand alignment of parallel sentences and on-the-fly estimation of translation models can yield massive reduction (up to 93% in our experiments) in development time as compared to a state-of-the-art system, while offering an interesting tradeoff as regards translation quality under some configurations. We show in particular that the absence of a development set can be quickly compensated by immediately using translated documents. Mots-clés : traduction automatique statistique ; développement efficace ; temps de calcul.

Towards a More Efficient Development of Statistical Machine Translation Systems (Vers un d'eveloppement plus efficace des syst`emes de traduction statistique : un peu de vert dans un monde de BLEU) [in French]

Résumé. Dans cet article de démonstration, nous introduisons un logiciel permettant de construire des tables de traduction de manière beaucoup plus rapide que ne le font les techniques à l’état de l’art. Cette accélération notable est obtenue par le biais d’un double échantillonnage : l’un permet la sélection d’un nombre limité de bi-phrases contenant les segments à traduire, l’autre réalise un alignement à la volée de ces bi-phrases pour extraire des exemples de traduction.

/pdf/much-faster-construction-of-smt-phrase-tables-from-large-4vbyj70xi6.pdf

(Much) Faster Construction of SMT Phrase Tables from Large-scale Parallel Corpora (Construction (tr`es) rapide de tables de traduction `a partir de grands bi-textes) [in French]

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Aurélien Max

Author Tools

Chat about Author