< Go Back

AMTA Main Conference Page

AMTA 2020 | 1st Workshop on Post-Editing in Modern-Day Translation

PEMDT1 @ AMTA 2020

September 8th October 6th, 12 to 3 p.m. Pacific Standard Time (UTC - 7)

Due to COVID-19, we are virtual now!

Orlando, Florida, USA

Background

Building on the success of past workshops that address post-editing, such as the ones held at AMTA 2018 and MT Summit 2019, we present PEMDT1 (https://www.naturallang.com/post-editing). Like its predecessors, this workshop will bring together post-editing translation tool users (practitioners) and researchers to compare and contrast how each use digital technology for translation. Specifically, the workshop focuses on novel advances in modern-day Computer-Assisted Tools (CAT) such as, but not limited to, Automatic Post-Editing (APE), Neural Machine Translation (NMT), and post-editing techniques and their usefulness as components in a practitioner's workflow. The workshop's aim is to gain a modern-day outlook on tools and the latest research in the post-editing sector. There will be open discussion amongst attendees along with invited speakers with an attempt to discern what is best for the post-editing field.

Final Program

Keynote Speaker

John Moran, Managing Director of Transpiral Ltd
Evaluating MT based on translation speed - a review of the status quo and a proposal for the future

John is a translator, trainer and programmer with an educational and research background in computational linguistics. His research interests revolve around measuring translator productivity as accurately and unobtrusively as possible by processing user activity data produced by translators in CAT tools.
In his presentation, John will summarize different ways desktop and web-based CAT tools can be used to capture working speed data for translators and outline what this means for end buyers of translation services, translation agencies and translators. He will also outline in broad terms how in an ideal world the research community could use this data to better evaluate MT based on how it makes translators more efficient. He will close by speculating how we might try to close the gap between this ideal world and the status quo.

Panelists

Sheila Castilho, Research Fellow at Dublin Center University

Sheila graduated in Linguistics and holds a joint Master in Natural Language Processing from the University of Wolverhampton –UK and the University of Algarve – PT. She has obtained a PhD in Machine translation Evaluation in 2016. She's authored several journal articles and book chapters on translation technology, post-editing of machine translation, user evaluation of machine translation, and translators’ perception of machine translation. She is a co-editor of the book 'Translation Quality Assessment: From Principles to Practice', published in 2018 by Springer. Her research interests include machine translation, post-editing, machine and human translation evaluation, document-level machine translation, usability, and translation technologies.

Alon Lavie, VP of Language Technologies at Unbabel

Alon is currently the VP of Language Technologies at Unbabel, where he leads and manages the US AI lab based in Pittsburgh, and provides strategic leadership for the AI R&D teams company-wide. He was also a senior manager at Amazon, where he led and managed the Amazon Machine Translation R&D group in Pittsburgh. He was a Research Professor at the Language Technologies Institute at Carnegie Mellon University with interests and activities focused on Machine Translation adaptation approaches with and without human feedback, applied to both high-resource language pairs as well as low-resource and minority languages.

Antonio Toral, Assistant Professor in Language Technology at the University of Groningen

Antonio holds a PhD in Computational Linguistics from the University of Alicante and has been researching in the field of Machine Translation (MT) since 2010. His research interests include the analysis of translations produced by machines and humans, the application of MT to literary texts and MT for under-resourced languages.

Patrick Simianer, Principal Research Scientist at Lilt

Patrick Simianer obtained a PhD in computational linguistics -- focusing on machine translation -- from Heidelberg University, Germany, and joined Lilt in 2017.

Schedule

20 minute talk on industry

   John Moran - Evaluating MT based on translation speed - a review of the status quo and a proposal for the future

4 industry demos of 10-15 minutes each

    Serene Su - Help Me! Those Free and/or Open Source Machine Translation Tools! - An Small Experiment with EN<>FR, EN<>ES and EN<>ZH translation
    Christopher Reid and Patrick McCrae - MT Quality Estimator - QUEST
    Luciana Ramos - MT Post Editing challenges: Training happy and successful posteditors
    Jonathan Mutal, Pierrette Bouillon, Perrine Schumacher and Johanna Gerlach - COPECO: a Collaborative Post-Editing Corpus in Pedagogical Context

3 research papers of 10-15 minutes each

   Maarit Koponen, Umut Sulubacak, Kaisa Vitikainen and Jörg Tiedemann - MT for Subtitling: Investigating professional translators' user experience and feedback
   Nico Herbig, Santanu Pal, Tim Düwel, Raksha Shenoy, Antonio Krüger and Josef van Genabith - Improving the Multi-Modal Post-Editing (MMPE) CAT Environment
     based on Professional Translators' Feedback
   Maria Stasimioti and Vilelmini Sosoni - Translation vs Post-editing of NMT Output: Insights from the English-Greek language pair

40 minute panel discussion

    Sheila Castilho, Patrick Simianer, Alon Lavie, Antonio Toral, John Ortega
    A "fireside chat" dialog amongst panelist and audience about new MT and PE technologies and how they affect speed and quality of translation.

Topics of Interest

We are highly interested in (1) original research papers and (2) demos on the topics below; however, we welcome all novel ideas that cover human involvement with digital translation tools:

Research Papers

Original papers (including short papers of 4 (four) to 6 (six) pages) are accepted for submission similar to those of AMTA 2020. Papers must not exceed 12 (twelve) pages with unlimited pages for references, and must be formatted according to the AMTA style guide: PDF version / LaTeX version / MS Word version. These papers will be rigorously reviewed for novelty and impact, and they will be published in the AMTA proceedings. They will be presented at the PEMDT workshop as oral presentations.

Submitted papers must be in PDF. To allow for blind reviewing, please do not include author names and affiliations within the paper, and avoid obvious self-references. Papers must be submitted to the START system (https://www.softconf.com/amta2020/pemdt1) by 11:59 pm (UTC-12), Wednesday, 26 August 2020.

Papers must represent new work that has not been previously published (pre-prints posted online on servers such as arXiv do not count as published papers, and thus are allowed to be submitted). It is the responsibility of the author(s) to inform the program organizers of any potential problem with respect to this requirement. Authors submitting a similar paper both to PEMDT and another conference or workshop must inform the organizers by email (see below for organizer information), specifying to which other conference or workshop they are submitting their work. If a paper is accepted at both PEMDT and another workshop/conference, then to appear at PEMDT it can either be presented at PEMDT as a full paper and withdrawn from the other conference, or it can be withdrawn from the proceedings, but still presented at PEMDT as a non-archival extended abstract. Full papers presented at the conference and included in the proceedings will also be hosted on the ACL Anthology.

Demos

We also invite one-page descriptions of interesting tools related to post-editing, including commercial products, in-house systems, research prototypes and open source software. Authors should be ready to present demos of the tools during the workshop. See Demo submission instructions below.

Demo submissions consist of a 1-page product description. They should not be anonymized. Please email your demo submissions directly to John Ortega by 11:59 pm (UTC-12), Wednesday, 26 August 2020.

Important Dates

Speakers

To be announced

Organizers

John E. Ortega (Universitat d’Alacant and New York University): jeo10@alu.ua.es

Marcello Federico (Amazon): marcfede@amazon.com

Constantin Orasan (University of Surrey): c.orasan@surrey.ac.uk

Maja Popovic (ADAPT Centre): maja.popovic@adaptcentre.ie

Program Committee

Lucia Specia (Imperial College London)

Maja Popovic (ADAPT Centre)

Kyunghyun Cho (New York University)

Daniel Torregrosa (World Intellectual Property Organization)

Nora Aranberri (Universidad del País Vasco)

Alberto Poncelas (ADAPT Centre)

Barry Haddow (University of Edinburgh)

Sheila Castilho (Dublin City University)

Constantin Orasan (University of Surrey)

Sharon O'Brien (ADAPT Centre)

John Moran (Transpiral)

Carlos Teixeira (IOTA and Trinity College Dublin)

Antonio Toral (University of Groningen)

Rohit Gupta (Apple)

Patrick Simianer (Lilt)

José Guilherme Camargo de Souza (eBay Inc.)

Michel Simard (National Research Council Canada)

Marco Turchi (Fondazione Bruno Kessler)

Matteo Negri (Fondazione Bruno Kessler)

Marcello Federico (Amazon)

Jeffrey Killman (University of North Carolina at Charlotte)

Alina Karakanta (Fondazione Bruno Kessler)

Miquel Esplà Gomis (Universitat d’Alacant)

Diego Bartolome (Transperfect)

Marcin Junczys-Dowmunt (Microsoft)

Kevin Knight (DiDi Labs)

Nicola Ueffing (eBay Inc.)

Alon Lavie (Unbabel)

Isabel Lacruz (Kent State University)

Adam Meyers (New York University)

Tsz Kin Lam (Heidelberg University)

Rebecca Knowles (National Research Council Canada)