THE FOURTH WORKSHOP ON TECHNOLOGIES FOR MT OF LOW-RESOURCE LANGUAGES (LoResMT 2021) https://sites.google.com/view/loresmt/ @ MT Summit XVIII – 2021 The 18th biennial conference of the International Association of Machine Translation 16-20 August 2021, Orlando, Florida, USA
INVITED TALKS 1. Mathias Müller Institut für Computerlinguistik, Universität Zürich “On Meaningful Evaluation of Machine Translation Systems” 2. To be announced SCOPE Based on the success of past low-resource machine translation (MT) workshops at AACL-IJCNLP 2020 (http://aacl2020.org/), MT Summit 2019 (https://www.mtsummit2019.com) and AMTA 2018 (https://amtaweb.org/), we introduce the fourth LoResMT workshop at MT Summit 2021. Like its predecessors, this workshop will bring together researchers and translators of low-resource languages to compare and contrast how each use digital technology for translation. Specifically, the workshop focuses on novel advances on the coverage of even more languages than past workshops with different geographical presence, degree of diffusion and digitalization. We solicit original work on low-resource translation which includes, but is not limited to, MT systems that include word tokenizers/de-tokenizers, word segmenters, morphological analyzers, and more. We furthermore invite work that includes MT systems based on neural networks along with their methods, natural language processing approaches, and overall coverage of low-resource languages. Additionally, novel work covering translations of COVID-related text and their practical use for low-resource communities are of high interest. The goal of this workshop is to begin to close the gap between low-resource translation systems and their practical use in the real world. Online systems and original research that can be used by native speakers of low-resource languages is of particular interest. Therefore, It will be beneficial if the evaluations of these tools in research papers include their impact on the quality of MT output and how they can be used in the real world. We are also happy to announce the introduction of a new shared task focused on the construction of machine translation systems for COVID-related texts. The task aims to encourage research on machine translation systems involving three low-resource language groups: (1) a sign language, (2) a language from the Americas and (3) a language from India. More information will be announced soon! TOPICS We are highly interested in (1) original research papers, (2) review/opinion papers, and (3) online systems on the topics below; however, we welcome all novel ideas that cover research on low-resource languages. - COVID-related corpora, their translations and corresponding NLP/MT systems - Neural machine translation for low-resource languages - Work that presents online systems for practical use by native speakers - Word tokenizers/de-tokenizers for specific languages - Word/morpheme segmenters for specific languages - Alignment/Re-ordering tools for specific language pairs - Use of morphology analyzers and/or morpheme segmenters in MT - Multilingual/cross-lingual NLP tools for MT - Corpora creation and curation technologies for low-resource languages - Review of available parallel corpora for low-resource languages - Research and review papers of MT methods for low-resource languages - MT systems/methods (e.g. rule-based, SMT, NMT) for low-resource languages - Pivot MT for low-resource languages - Zero-shot MT for low-resource languages - Fast building of MT systems for low-resource languages - Re-usability of existing MT systems for low-resource languages - Machine translation for language preservation SUBMISSION INFORMATION There are two types of submissions in the workshop. For research, review and position papers, the length of each paper should be at least four (4) and not exceed eight (8) pages, plus unlimited pages for references. For system demonstration papers, the limit is four (4) pages. Submissions should be formatted according to the official MT Summit 2021 style templates (PDF, LaTeX, Word). Accepted papers will be published on-line in the MT Summit 2021 proceedings and will be presented at the conference either orally or as a poster. Submissions must be anonymized and should be done using the official conference management system (https://cmt3.research.microsoft.com/MTSUMMIT2021). Scientific papers that have been or will be submitted to other venues must be declared as such, and must be withdrawn from the other venues if accepted and published at LoResMT. The review will be double-blind. We would like to encourage authors to cite papers written in ANY language that are related to the topics, as long as both original bibliographic items and their corresponding English translations are provided. Registration will be handled by the main conference. (To be announced) IMPORTANT DATES March 25, 2021 – Call for papers released April 22, 2021 – Second call for papers May 20, 2021 – Third call for papers June 17 , 2021 – Paper submissions due July 8 , 2021 – Notification of acceptance July 15, 2021 – Camera-ready due August 5, 2021 – Video recordings due August 16, 2021 - LoResMT workshop CONTACT LoResMT 2021 Workshop Chair: John Ortega (jort...@cs.nyu.edu) Shared Task Chairs: Atul Kr. Ojha (atulkumar.o...@insight-centre.org) Katharina Kann (katharina.k...@colorado.edu) Chao-Hong Liu (ch....@acm.org) ORGANIZING COMMITTEE (listed alphabetically) Atul Kr. Ojha DSI, National University of Ireland Galway & Panlingua Language Processing LLP Chao-Hong Liu Potamu Research Ltd Jade Abbott Retro Rabbit John Ortega New York University Jonathan Washington Swarthmore College Katharina Kann University of Colorado at Boulder Nathaniel Oco National University (Philippines) Surafel Melaku Lakew Amazon AI Tommi A Pirinen University of Hamburg Valentin Malykh Huawei Noah’s Ark lab and Kazan Federal University Varvara Logacheva Skolkovo Institute of Science and Technology Xiaobing Zhao Minzu University of China
_______________________________________________ Mt-list site list Mt-list@eamt.org http://lists.eamt.org/mailman/listinfo/mt-list