@inproceedings{khalid-etal-2026-leveraging,
    title = "Leveraging {C}o{H}ere Multilingual Embeddings and Inverted Softmax Retrieval for Automatic Parallel Sentence Alignment in Low-Resource Languages",
    author = "Khalid, Abubakar Auwal  and
      Borodo, Salisu Musa  and
      Imam, Amina Abubakar",
    editor = "Chimoto, Everlyn Asiko  and
      Lignos, Constantine  and
      Muhammad, Shamsuddeen  and
      Abdulmumin, Idris  and
      Siro, Clemencia  and
      Adelani, David Ifeoluwa",
    booktitle = "Proceedings of the 7th Workshop on {A}frican Natural Language Processing ({A}frica{NLP} 2026)",
    month = mar,
    year = "2026",
    address = "Rabat, Morocco",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/manual-author-scripts/2026.africanlp-main.4/",
    pages = "37--43",
    ISBN = "979-8-89176-364-7",
    abstract = "We present an improved method for automaticparallel sentence alignment in low- resourcelanguages. We used CoHere multilingualembeddings and inverted softmax retrieval.Our technique achieved a higher F1-score of78.30{\%} on the MAFAND-MT test set, comparedto the existing technique{'}s 54.75{\%}. Precisionand recall have shown similar performance.We assessed the quality of the extracted data bydemonstrating that it outperforms the existingtechnique in terms of low-resource translationperformance."
}