Emmanuelle Esperança-Rodier

Emmanuelle Esperança-Rodier
Université Grenoble Alpes · Computer Science

Doctor of Computational Linguistics

About

20
Publications
3,265
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
69
Citations
Introduction
Emmanuelle Esperança-Rodier currently works at the Computer Science, Université Grenoble Alpes. Emmanuelle does research in Computational Linguistics. Their most recent publication is 'Uses and perceptions of machine translation at the European Commission'.

Publications

Publications (20)
Chapter
Full-text available
Cet ouvrage collectif rassemble vingt-quatre contributions scientifiques sélectionnées parmi les présentations des onzièmes journées du réseau Lexicologie, Terminologie, Traduction. Ces journées intitulées « Lexique(s) et genre(s) textuel(s) : approches sur corpus » eurent lieu à Grenoble, France du 25 au 28 septembre 2018. Les études lexicales ont...
Preprint
Full-text available
We conduct in this work an evaluation study comparing offline and online neural machine translation architectures. Two sequence-to-sequence models: convolutional Pervasive Attention (Elbayad et al. 2018) and attention-based Transformer (Vaswani et al. 2017) are considered. We investigate, for both architectures, the impact of online decoding constr...
Poster
Full-text available
Description of the online collaboration platform ACCOLÉ.
Conference Paper
Full-text available
This article presents a platform, named ACCOLÉ, for the collaborative annotation of translation errors. ACCOLÉ offers a range of services that allow simplified management of corpora and error typologies, annotation of effective errors, collaborative discussion during annotation, and finally different kinds of search in corpora. ACCOLÉ allows the an...
Conference Paper
Full-text available
Translation process research has developed tools to gather and analyse empirical data, but while a variety of measures have proved useful and reliable to assess machine translation post-editing effort (see e.g. Vieira 2016: 42), translation processes are seldom considered when assessing the relevance of a given Machine translation post-editing (MTP...
Chapter
Full-text available
Multiword expressions (MWEs) are known to be widespread in most languages, but how can we actually identify them in texts? How can we account for the diverse nature of these multiword expressions with a consistent typology? This paper aims to address this topic by carrying out two tasks: (1) conducting a small survey with expert linguists on severa...
Conference Paper
Full-text available
Cette étude s'attache à évaluer la qualité d'un système de traduction probabiliste état de l'art, LIG-Moses (Potet, 2010), du français vers l'anglais, des expressions poly-lexicales, décrites selon Tutin (2015), dans un document technique, à l'aide de la typologie d'erreurs de Vilar (2006). Nous nous attachons à montrer si l'outil est utilisable pa...
Conference Paper
Full-text available
The goal of our research is to develop an automatic pictogram generation tool from speech to help the social circle of users of Alternative and Augmentative Communication to communicate among themselves. We described here the issues of such a tool, we then detail our development methodology and finally we describe our evaluation protocol.
Conference Paper
Full-text available
Cet article présente les travaux d'analyse d'erreurs de 2 systèmes de TA maison, l'un probabiliste et l'autre neuronal. Après une description du corpus et des systèmes, nous analysons les deux systèmes en fonction d'une typologie d'erreurs en nous arrêtant sur quelques exemples de phrases pour lesquelles les deux systèmes ont effectué le même type...
Conference Paper
Full-text available
RESUME Cet article présente une plateforme pour l'édition collaborative d'erreurs de traduction. Cette plateforme, nommée ACCOLÉ (Annotation Collaborative d'erreurs de traduction pour COrpus aLignÉs), propose une palette de services innovants permettant de répondre aux besoins modernes d'analyse d'erreurs de traduction : gestion simplifiée des corp...
Conference Paper
Full-text available
Statistical and neural approaches have permitted fast improvement in the quality of machine translation, but we are yet to discover how those technologies can best “serve translators and end users of translations” (Kenny, 2017). To address human issues in machine translation, we propose an interdisciplinary approach linking Translation Studies, Nat...
Conference Paper
Full-text available
Current research on translation technology seeks to integrate physical, cognitive and organisational ergonomics (Lavault-Olléon, 2011) and uses insights from the situated cognition paradigm (Risku, 2010) to bring together social and technical perspectives on fastly-evolving human-computer interactions (Cadwell et al. 2016). Even though these trends...
Conference Paper
La difficile identification des expressions polylexicales dans les textes : critères de décision et annotation Il est courant maintenant de considérer que la langue est largement préconstruite et que la phraséologie y occupe une place majeure. « Tout est idiomatique dans les langues » proclame ainsi F.J. Hausmann (1997). Le principe idiomatique (id...
Chapter
This paper examines the frequency and functions of English and French opinion markers in 60 presentation transcripts of the EIIDA corpus in Linguistics and in Chemistry, Geochemistry, Marine, and Water Sciences. These functions, found in all four sub-corpora, include highlighting a general or strong opinion, proposing a hypothesis or negotiating wi...
Conference Paper
Full-text available
Nowadays, Statistical Machine Translation (SMT) is widely available. Nevertheless, using Machine Translation at its best is not an easy task. Structures appearing sporadically trigger most of the regular mistakes of SMT systems. We work on one of those structures: the MultiWord Expressions (MWE). Our study aims at evaluating the quality of MWE tran...
Conference Paper
Full-text available
This paper presents an experiment of annotation of MWEs in French. The corpus used is made of several genres (news, novel, scientific report, film subtitles) and includes a rich annotation scheme including several kinds of MWEs from collocations to routines and full phrasemes. The annotation is performed semi-automatically with finite-state transdu...
Article
Full-text available
The aim is to develop an interactive and iterative translation system able to adapt and improve itself rapidly using user's feedbacks (collected as translation post-editions). We present a preliminary study in which three methods for integrating feedbacks are tested. The results show that, despite the difficulty to measure the system improvement wi...

Network

Cited By

Projects

Project (1)