@inproceedings{nllb2022,
  title     = {No Language Left Behind: Scaling Human-Centered Machine Translation},
  author    = {Costa-jussà, Marta R. and Cross, James and et al.},
  booktitle = {Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year      = {2022},
  publisher = {Association for Computational Linguistics},
  url       = {https://aclanthology.org/2022.emnlp-main.9}
}
@inproceedings{sikasote-etal-2023-big,
    title = "{BIG}-{C}: a Multimodal Multi-Purpose Dataset for {B}emba",
    author = "Sikasote, Claytone  and
      Mukonde, Eunice  and
      Alam, Md Mahfuz Ibn  and
      Anastasopoulos, Antonios",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.115",
    doi = "10.18653/v1/2023.acl-long.115",
    pages = "2062--2078",
    abstract = "We present BIG-C (Bemba Image Grounded Conversations), a large multimodal dataset for Bemba. While Bemba is the most populous language of Zambia, it exhibits a dearth of resources which render the development of language technologies or language processing research almost impossible. The dataset is comprised of multi-turn dialogues between Bemba speakers based on images, transcribed and translated into English. There are more than 92,000 utterances/sentences, amounting to more than 180 hours of audio data with corresponding transcriptions and English translations. We also provide baselines on speech recognition (ASR), machine translation (MT) and speech translation (ST) tasks, and sketch out other potential future multimodal uses of our dataset. We hope that by making the dataset available to the research community, this work will foster research and encourage collaboration across the language, speech, and vision communities especially for languages outside the {``}traditionally{''} used high-resourced ones. All data and code are publicly available: [\url{https://github.com/csikasote/bigc}](\url{https://github.com/csikasote/bigc}).",
}
Copy@inproceedings{wang-etal-2024-afrimte,
    title = "{A}fri{MTE} and {A}fri{COMET}: Enhancing {COMET} to Embrace Under-resourced {A}frican Languages",
    author = "Wang, Jiayi and Adelani, David and Agrawal, Sweta and Masiak, Marek and Rei, Ricardo and Briakou, Eleftheria and Carpuat, Marine and He, Xuanli and others",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = "jun",
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.334/",
    doi = "10.18653/v1/2024.naacl-long.334",
    pages = "5997--6023"
}
@inproceedings{wang2024evaluating,
  title={Evaluating WMT 2024 Metrics Shared Task Submissions on AfriMTE (the African Challenge Set)},
  author={Wang, Jiayi and Adelani, David Ifeoluwa and Stenetorp, Pontus},
  booktitle={Proceedings of the Ninth Conference on Machine Translation},
  pages={505--516},
  year={2024}
}
@inproceedings{freitag2024llms,
  title={Are LLMs breaking MT metrics? results of the WMT24 metrics shared task},
  author={Freitag, Markus and Mathur, Nitika and Deutsch, Daniel and Lo, Chi-Kiu and Avramidis, Eleftherios and Rei, Ricardo and Thompson, Brian and Blain, Frederic and Kocmi, Tom and Wang, Jiayi and others},
  booktitle={Proceedings of the Ninth Conference on Machine Translation},
  pages={47--81},
  year={2024}
}