LoResMT 2022
Workshop on Low-Resource Machine Translation
The fifth Low Resource Machine Translation (LoResMT 2022) workshop was held by the 29th International Conference on Computational Linguistics (COLING) on 16 October, 2022, in Gyeongju, Republic of Korea.
- Website: sites.google.com/view/loresmt/
- Github: github.com/loresmt
Schedule
09:00 - 09:15 | Opening remarks Workshop chairs |
09:15 - 10:05 | Invited talk Mining Methods for Low Resource MT Vishrav Chaudhary, Microsoft Turing Chair: Atul Kr. Ojha |
10:05 - 10:30 | Q&A Session 1 Chair: Ekaterina Vylomova |
Very Low Resource Sentence Alignment: Luhya and Swahili Everlyn Chimoto, Bruce Bassett | |
A Preordered RNN Layer Boosts Neural Machine Translation in Low Resource Settings Mohaddeseh Bastan, Shahram Khadivi | |
10:30 - 11:00 | ☕️ |
11:00 - 12:30 | Q&A Session 2 Chair: Jonathan Washington |
Known Words Will Do: Unknown Concept Translation via Lexical Relations Winston Wu, David Yarowsky | |
The only chance to understand: machine translation of the severely endangered low-resource languages of Eurasia Anna Mosolova, Kamel Smaili | |
Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaican Nathaniel Robinson, Cameron Hogan, Nancy Fulda, David R. Mortensen | |
12:30 - 14:00 | 🍴 |
14:00 - 14:55 | Invited talk Low Resource Machine Translation- A Perspective Pushpak Bhattacharyya, Indian Institute of Technology Bombay Chair: Chao-Hong Liu |
14:55 - 15:30 | Q&A Session 3 Chair: Nathaniel Oco |
Augmented Bio-SBERT: Improving Performance For Pairwise Sentence Tasks in Bio-medical Domain Sonam Pankaj, Amit Gautam | |
Machine Translation for a very Low-Resource Language - Layer Freezing approach on Transfer Learning Amartya Chowdhury, Deepak K. T., Samudra Vijaya K, S. R. Mahadeva Prasanna | |
HFT: High Frequency Tokens for Low-Resource NMT Edoardo Signoroni, Pavel Rychlý | |
15:30 - 16:00 | ☕️ |
16:00 - 17:00 | Q&A Session 4 Chair: Valentin Malykh |
Romanian language translation in the RELATE platform Vasile Pais, Maria Mitrofan, Andrei-Marius Avram | |
Translating Spanish into Spanish Sign Language: Combining Rules and Data-driven Approaches Luis Chiruzzo, Euan McGill, Santiago Egea-Gómez, Horacio Saggion | |
17:00 - 17:50 | Q&A Session 5 Chair: Xiaobing Zhao |
Benefiting from Language Similarity in the Multilingual MT Training: Case Study of Indonesian and Malaysian Alberto Poncelas, Johanes Effendi | |
Multiple Pivot Languages and Strategic Decoder Initialization helps Neural Machine Translation Shivam Mhaskar, Pushpak Bhattacharyya | |
Exploring Word Alignment Towards an Efficient Sentence Aligner for Filipino and Cebuano Languages Jenn Leana Fernandez, Kristine Mae M. Adlaon | |
Aligning Word Vectors on Low-Resource Languages with Wiktionary Mike Lzbicki | |
17:50 - 18:00 | Closing remarks Workshop chairs |
Important dates
Submission deadline | 30 July |
Notification of acceptance | 22 August |
Camera-ready papers deadline | 5 September |
LoResMT workshop | 16 October |
All deadlines are anywhere on Earth.
Topics
- COVID-related corpora, their translations and corresponding natural language processing/machine translation systems
- Neural machine translation for low-resource languages
- Work that presents online systems for practical use by native speakers
- Word tokenisers/de-tokenisers for specific languages
- Word/morpheme segmenters for specific languages
- Alignment/Re-ordering tools for specific language pairs
- Use of morphology analysers and/or morpheme segmenters in machine translation
- Multilingual/cross-lingual natural language processing tools for machine translation
- Corpora creation and curation technologies for low-resource languages
- Review of available parallel corpora for low-resource languages
- Research and review papers of machine translation methods for low-resource languages
- Machine translation systems/methods (for example, rule-based, statistical, neural machine translation) for low-resource languages
- Pivot machine translation for low-resource languages
- Zero-shot machine translation for low-resource languages
- Fast building of machine translation systems for low-resource languages
- Re-usability of existing machine translation systems for low-resource languages
- Machine translation for language preservation