Link Search Menu Expand Document

LoResMT 2021

Workshop on Low-Resource Machine Translation


The fourth Low-Resource Machine Translation workshop (LoResMT 2021) was held online in the MT Summit 2021 on 16 August, 2021.

sites.google.com/view/loresmt/home?authuser=0

Shared tasks

The new shared tasks focusing on the building of MT systems for COVID-related texts aims to encourage research on MT systems involving three low-resource language pairs:

  • Taiwanese Sign Language <> Traditional Chinese
  • English <> Irish
  • English <> Marathi

Schedule

   
08:00 - 08:15 Opening remarks
08:30 - 09:15 On Meaningful Evaluation of Machine Translation Systems
Mathias Müller
Institut für Computerlinguistik
Universität Zürich
09:30 - 10:15 MT for low-resource languages: progress and open problems
Barry Haddow
Aveni and University of Edinburgh
10:30 - 11:15 Challenges and Advances in MT Systems for African Languages
Catherine Muthoni Gitau
African Institute for Mathematical Science
11:30 - 12:30 Trustworthy human evaluation frameworks for MT
Mona Diab
Facebook and George Washington University
13:00 - 13:45 🍴
14:00 - 16:00 Research Papers Session 1
  Zero-Shot Neural Machine Translation with Self-Learning Cycle
Surafel Lakew, Matteo Negri, Marco Turchi
  A Comparison of Different NMT Approaches to Low-Resource Dutch-Albanian Machine Translation
Arbnor Rama and Eva Vanmassenhove
  Small-Scale Cross-Language Authorship Attribution on Social Media Comments
Benjamin Murauer and Gunther Specht
  EnKhCorp1.0: An English-Khasi Corpus
Sahinur Rahman Laskar, Abdullah Faiz Ur Rahman Khilji, Darsh Kaushik, Dr. Partha Pakray and Sivaji Bandyopadhyay
16:30-17:30 Research Papers Session 2
  Active Learning for Massively Parallel Translation of Constrained Text into Low Resource Languages
Zhong Zhou and Alex Waibel
  Manipuri-English Machine Translation using Comparable Corpus
Lenin Laitonjam and Ranbir Sanasam
17:30-18:00 ☕️
18:00-20:00 Research Papers Session 3
  Morphologically-Guided Segmentation For Translation of Agglutinative Low-Resource Languages
William Chen and Brett Fazio
  Structural Biases for Improving Transformers on Translation into Morphologically Rich Languages
Paul Soulos, Sudha Rao, Caitlin Smith, Eric Rosen, Asli Celikyilmaz, R. Thomas Mccoy, Yichen Jiang, Coleman Haley, Roland Fernandez, Hamid Palangi, Jianfeng Gao and Paul Smolensky
  Love Thy Neighbor: Combining Two Neighboring Low-Resource Languages for Translation
John Ortega, Richard Castro Mamani, and Jaime Rafael Montoya Samame
  Dealing with the Paradox of Quality Estimation
Sugyeong Eo, Chanjun Park, Jaehyung Seo, Hyeonseok Moon, and Heuiseok Lim
20:30-21:30 Findings of the shared Task
  A3-108 Machine Translation System for LoResMT Shared Task @MT Summit 2021 Conference
Saumitra Yadav, and Manish Shrivastava
  Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021
Karthik Puranik, Adeep Hande, Ruba Priyadharshini, Thenmozi D, Anbukkarasi Sampath, Kingston Pal Thamburaj and Bharathi Raja Chakravarthi
  Evaluating the Performance of Back-translation for Low Resource English-Marathi Language Pair: CFILT-IITBombay @ LoResMT 2021
Aditya Jain, Shivam Mhaskar and Pushpak Bhattacharyya
  The UCF Systems for the LoResMT 2021 Machine Translation Shared Task
William Chen and Brett Fazio
  Machine Translation in the Covid domain: an English-Irish case study for LoResMT 2021
Séamus Lankford, Haithem Afli and Andy Way
  English-Marathi Neural Machine Translation for LoResMT 2021
Vandan Mujadia and Dipti Misra Sharma
21:30-22:15 Closing remarks

Edit this article →

Machine Translate is created and edited by contributors like you!

Learn more about contributing →

Licensed under CC-BY-SA-4.0.

Cite this article →