@inproceedings{chimoto-bassett-2022-low,
    title = "Very Low Resource Sentence Alignment: Luhya and {S}wahili",
    author = "Chimoto, Everlyn Asiko  and
      Bassett, Bruce A.",
    editor = "Ojha, Atul Kr.  and
      Liu, Chao-Hong  and
      Vylomova, Ekaterina  and
      Abbott, Jade  and
      Washington, Jonathan  and
      Oco, Nathaniel  and
      Pirinen, Tommi A  and
      Malykh, Valentin  and
      Logacheva, Varvara  and
      Zhao, Xiaobing",
    booktitle = "Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)",
    month = oct,
    year = "2022",
    address = "Gyeongju, Republic of Korea",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2022.loresmt-1.1/",
    pages = "1--8",
    abstract = "Language-agnostic sentence embeddings generated by pre-trained models such as LASER and LaBSE are attractive options for mining large datasets to produce parallel corpora for low-resource machine translation. We test LASER and LaBSE in extracting bitext for two related low-resource African languages: Luhya and Swahili. For this work, we created a new parallel set of nearly 8000 Luhya-English sentences which allows a new zero-shot test of LASER and LaBSE. We find that LaBSE significantly outperforms LASER on both languages. Both LASER and LaBSE however perform poorly at zero-shot alignment on Luhya, achieving just 1.5{\%} and 22.0{\%} successful alignments respectively (P@1 score). We fine-tune the embeddings on a small set of parallel Luhya sentences and show significant gains, improving the LaBSE alignment accuracy to 53.3{\%}. Further, restricting the dataset to sentence embedding pairs with cosine similarity above 0.7 yielded alignments with over 85{\%} accuracy."
}