Low Resource Machine Translation

2025

1. AmericasNLP

   Machine Translation Metrics for Indigenous Languages Using Fine-tuned Semantic Embeddings

   Nathaniel Krasner^*, Justin Vasselli^*, Belu Ticona, Antonios Anastasopoulos, and Chi-Kiu Lo

   In Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP) Code here , May 2025

   Bib PDF

   @inproceedings{krasner-etal-2025-machine,
     title = {Machine Translation Metrics for Indigenous Languages Using Fine-tuned Semantic Embeddings},
     author = {Krasner, Nathaniel and Vasselli, Justin and Ticona, Belu and Anastasopoulos, Antonios and Lo, Chi-Kiu},
     editor = {Mager, Manuel and Ebrahimi, Abteen and Pugh, Robert and Rijhwani, Shruti and Von Der Wense, Katharina and Chiruzzo, Luis and Coto-Solano, Rolando and Oncevay, Arturo},
     booktitle = {Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)},
     month = may,
     year = {2025},
     address = {Albuquerque, New Mexico},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.americasnlp-1.11/},
     pages = {100--104},
     isbn = {979-8-89176-236-7},
   }

2. VarDial

   

   Large Language Models as a Normalizer for Transliteration and Dialectal Translation

   Md Mahfuz Ibn Alam, and Antonios Anastasopoulos

   In Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects Code here , Jan 2025

   Abs Bib PDF

   NLP models trained on standardized language data often struggle with variations. We assess various Large Language Models (LLMs) for transliteration and dialectal normalization. Tuning open-source LLMs with as little as 10,000 parallel examples using LoRA can achieve results comparable to or better than closed-source LLMs. We perform dialectal normalization experiments for twelve South Asian languages and dialectal translation experiments for six language continua worldwide. The dialectal normalization task can also be a preliminary step for the downstream dialectal translation task. Among the six languages used in dialectal translation, our approach enables Italian and Swiss German to surpass the baseline model by 21.5 and 25.8 BLEU points, respectively.

   @inproceedings{alam-anastasopoulos-2025-large,
     title = {Large Language Models as a Normalizer for Transliteration and Dialectal Translation},
     author = {Alam, Md Mahfuz Ibn and Anastasopoulos, Antonios},
     editor = {Scherrer, Yves and Jauhiainen, Tommi and Ljube{\v{s}}i{\'c}, Nikola and Nakov, Preslav and Tiedemann, Jorg and Zampieri, Marcos},
     booktitle = {Proceedings of the 12th Workshop on NLP for Similar Languages, Varieties and Dialects},
     month = jan,
     year = {2025},
     address = {Abu Dhabi, UAE},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2025.vardial-1.5/},
     pages = {39--67},
   }

2024

1. LREC-COLING

   

   Language and Speech Technology for Central Kurdish Varieties

   Sina Ahmadi, Daban Jaff, Md Mahfuz Ibn Alam, and Antonios Anastasopoulos

   In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024) code here , May 2024

   Abs Bib PDF

   Kurdish, an Indo-European language spoken by over 30 million speakers, is considered a dialect continuum and known for its diversity in language varieties. Previous studies addressing language and speech technology for Kurdish handle it in a monolithic way as a macro-language, resulting in disparities for dialects and varieties for which there are few resources and tools available. In this paper, we take a step towards developing resources for language and speech technology for varieties of Central Kurdish, creating a corpus by transcribing movies and TV series as an alternative to fieldwork. Additionally, we report the performance of machine translation, automatic speech recognition, and language identification as downstream tasks evaluated on Central Kurdish subdialects. Data and models are publicly available under an open license at https://github.com/sinaahmadi/CORDI.

   @inproceedings{ahmadi-etal-2024-language,
     title = {Language and Speech Technology for {C}entral {K}urdish Varieties},
     author = {Ahmadi, Sina and Jaff, Daban and Alam, Md Mahfuz Ibn and Anastasopoulos, Antonios},
     editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
     booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
     month = may,
     year = {2024},
     address = {Torino, Italia},
     publisher = {ELRA and ICCL},
     url = {https://aclanthology.org/2024.lrec-main.877/},
     pages = {10034--10045},
   }

2. WMT

   Findings of the WMT 2024 Shared Task of the Open Language Data Initiative

   Jean Maillard, Laurie Burchell, Antonios Anastasopoulos, Christian Federmann, Philipp Koehn, and Skyler Wang

   In Proceedings of the Ninth Conference on Machine Translation, Nov 2024

   Abs DOI Bib PDF

   We present the results of the WMT 2024 shared task of the Open Language Data Initiative. Participants were invited to contribute to the FLORES+ and MT Seed multilingual datasets, two foundational open resources that facilitate the organic expansion of language technology‘s reach. We accepted ten submissions covering 16 languages, which extended the range of languages included in the datasets and improved the quality of existing data.

   @inproceedings{maillard-etal-2024-findings,
     title = {Findings of the {WMT} 2024 Shared Task of the Open Language Data Initiative},
     author = {Maillard, Jean and Burchell, Laurie and Anastasopoulos, Antonios and Federmann, Christian and Koehn, Philipp and Wang, Skyler},
     editor = {Haddow, Barry and Kocmi, Tom and Koehn, Philipp and Monz, Christof},
     booktitle = {Proceedings of the Ninth Conference on Machine Translation},
     month = nov,
     year = {2024},
     address = {Miami, Florida, USA},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.wmt-1.4/},
     doi = {10.18653/v1/2024.wmt-1.4},
     pages = {110--117},
   }

3. IWSLT

   FINDINGS OF THE IWSLT 2024 EVALUATION CAMPAIGN

   Ibrahim Said Ahmad, Antonios Anastasopoulos, Ondřej Bojar, Claudia Borg, Marine Carpuat, Roldano Cattoni, Mauro Cettolo, William Chen, Qianqian Dong, Marcello Federico, and 34 more authors

   In Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024), Aug 2024

   Abs DOI Bib

   This paper reports on the shared tasks organized by the 21st IWSLT Conference. The shared tasks address 7 scientific challenges in spoken language translation: simultaneous and offline translation, automatic subtitling and dubbing, speech-to-speech translation, dialect and low-resource speech translation, and Indic languages. The shared tasks attracted 17 teams whose submissions are documented in 27 system papers. The growing interest towards spoken language translation is also witnessed by the constantly increasing number of shared task organizers and contributors to the overview paper, almost evenly distributed across industry and academia.

   @inproceedings{ahmad-etal-2024-findings,
     title = {{FINDINGS} {OF} {THE} {IWSLT} 2024 {EVALUATION} {CAMPAIGN}},
     author = {Ahmad, Ibrahim Said and Anastasopoulos, Antonios and Bojar, Ond{\v{r}}ej and Borg, Claudia and Carpuat, Marine and Cattoni, Roldano and Cettolo, Mauro and Chen, William and Dong, Qianqian and Federico, Marcello and Haddow, Barry and Javorsk{\'y}, D{\'a}vid and Krubi{\'n}ski, Mateusz and Lam, Tsz Kin and Ma, Xutai and Mathur, Prashant and Matusov, Evgeny and Maurya, Chandresh and McCrae, John and Murray, Kenton and Nakamura, Satoshi and Negri, Matteo and Niehues, Jan and Niu, Xing and Ojha, Atul Kr. and Ortega, John and Papi, Sara and Pol{\'a}k, Peter and Posp{\'i}{\v{s}}il, Adam and Pecina, Pavel and Salesky, Elizabeth and Sethiya, Nivedita and Sarkar, Balaram and Shi, Jiatong and Sikasote, Claytone and Sperber, Matthias and St{\"u}ker, Sebastian and Sudoh, Katsuhito and Thompson, Brian and Waibel, Alex and Watanabe, Shinji and Wilken, Patrick and Zem{\'a}nek, Petr and Zevallos, Rodolfo},
     editor = {Salesky, Elizabeth and Federico, Marcello and Carpuat, Marine},
     booktitle = {Proceedings of the 21st International Conference on Spoken Language Translation (IWSLT 2024)},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand (in-person and online)},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2024.iwslt-1.1/},
     doi = {10.18653/v1/2024.iwslt-1.1},
     pages = {1--11},
   }

2023

1. IWSLT

   GMU Systems for the IWSLT 2023 Dialect and Low-resource Speech Translation Tasks

   Jonathan Mbuya, and Antonios Anastasopoulos

   In Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023), Jul 2023

   Abs DOI Bib PDF

   This paper describes the GMU Systems for the IWSLT 2023 Dialect and Low-resource Speech Translation Tasks. We submitted systems for five low-resource tasks and the dialectal task. In this work, we explored self-supervised pre-trained speech models and finetuned them on speech translation downstream tasks. We use the Wav2vec 2.0, XLSR-53, and Hubert as self-supervised models. Unlike Hubert, Wav2vec 2.0 and XLSR-53 achieve the best results when we remove the top three layers. Our results show that Wav2vec 2.0 and Hubert perform similarly with their relative best configuration. In addition, we found that Wav2vec 2.0 pre-trained on audio data of the same language as the source language of a speech translation model achieves better results. For the low-resource setting, the best results are achieved using either the Wav2vec 2.0 or Hubert models, while XLSR-53 achieves the best results for the dialectal transfer task. We find that XLSR-53 does not perform well for low-resource tasks. Using Wav2vec 2.0, we report close to 2 BLEU point improvements on the test set for the Tamasheq-French compared to the baseline system at the IWSLT 2022.

   @inproceedings{mbuya-anastasopoulos-2023-gmu,
     title = {{GMU} Systems for the {IWSLT} 2023 Dialect and Low-resource Speech Translation Tasks},
     author = {Mbuya, Jonathan and Anastasopoulos, Antonios},
     editor = {Salesky, Elizabeth and Federico, Marcello and Carpuat, Marine},
     booktitle = {Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)},
     month = jul,
     year = {2023},
     address = {Toronto, Canada (in-person and online)},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2023.iwslt-1.24/},
     doi = {10.18653/v1/2023.iwslt-1.24},
     pages = {269--276},
   }

2022

1. WMT

   Language Adapters for Large-Scale MT: The GMU System for the WMT 2022 Large-Scale Machine Translation Evaluation for African Languages Shared Task

   Md Mahfuz Ibn Alam, and Antonios Anastasopoulos

   In Proceedings of the Seventh Conference on Machine Translation (WMT), Dec 2022

   Abs Bib PDF

   This report describes GMU‘s machine translation systems for the WMT22 shared task on large-scale machine translation evaluation for African languages. We participated in the constrained translation track where only the data listed on the shared task page were allowed, including submissions accepted to the Data track. Our approach uses models initialized with DeltaLM, a generic pre-trained multilingual encoder-decoder model, and fine-tuned correspondingly with the allowed data sources. Our best submission incorporates language family and language-specific adapter units; ranking ranked second under the constrained setting.

   @inproceedings{alam-anastasopoulos-2022-language,
     title = {Language Adapters for Large-Scale {MT}: The {GMU} System for the {WMT} 2022 Large-Scale Machine Translation Evaluation for {A}frican Languages Shared Task},
     author = {Alam, Md Mahfuz Ibn and Anastasopoulos, Antonios},
     editor = {Koehn, Philipp and Barrault, Lo{\"i}c and Bojar, Ond{\v{r}}ej and Bougares, Fethi and Chatterjee, Rajen and Costa-juss{\`a}, Marta R. and Federmann, Christian and Fishel, Mark and Fraser, Alexander and Freitag, Markus and Graham, Yvette and Grundkiewicz, Roman and Guzman, Paco and Haddow, Barry and Huck, Matthias and Jimeno Yepes, Antonio and Kocmi, Tom and Martins, Andr{\'e} and Morishita, Makoto and Monz, Christof and Nagata, Masaaki and Nakazawa, Toshiaki and Negri, Matteo and N{\'e}v{\'e}ol, Aur{\'e}lie and Neves, Mariana and Popel, Martin and Turchi, Marco and Zampieri, Marcos},
     booktitle = {Proceedings of the Seventh Conference on Machine Translation (WMT)},
     month = dec,
     year = {2022},
     address = {Abu Dhabi, United Arab Emirates (Hybrid)},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2022.wmt-1.99/},
     pages = {1015--1033},
   }