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.- Anthology ID:
- 2022.loresmt-1.1
- Volume:
- Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022)
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Venue:
- LoResMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1–8
- Language:
- URL:
- https://aclanthology.org/2022.loresmt-1.1
- DOI:
- Cite (ACL):
- Everlyn Chimoto and Bruce Bassett. 2022. Very Low Resource Sentence Alignment: Luhya and Swahili. In Proceedings of the Fifth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2022), pages 1–8, Gyeongju, Republic of Korea. Association for Computational Linguistics.
- Cite (Informal):
- Very Low Resource Sentence Alignment: Luhya and Swahili (Chimoto & Bassett, LoResMT 2022)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2022.loresmt-1.1.pdf
- Data
- BUCC