Metraipolis › archive › dc_c337cc7941d3
KinyaEmbed: Contrastive Sentence Embeddings for Kinyarwanda via Multi-Stage Curriculum Training — arXiv:2608.26941
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.26941
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T15:20:05.629Z
- SHA-256 of the archived text
d900783246e2c4a4f4e9eba1ef2e1b1ddbf7981fe54706a982be82c18b0ea2c7- Stable URL of this page
https://metraipolis.com/documento/dc_c337cc7941d3
How to cite
KinyaEmbed: Contrastive Sentence Embeddings for Kinyarwanda via Multi-Stage Curriculum Training — arXiv:2608.26941 — arXiv (en), https://arxiv.org/abs/2608.26941 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c337cc7941d3 (Metraipolis archive dc_c337cc7941d3, sha256 d900783246e2c4a4f4e9eba1ef2e1b1ddbf7981fe54706a982be82c18b0ea2c7)
BibTeX
@misc{dcc337cc7941d3,
title = {KinyaEmbed: Contrastive Sentence Embeddings for Kinyarwanda via Multi-Stage Curriculum Training — arXiv:2608.26941},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.26941},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c337cc7941d3; sha256 d900783246e2c4a4f4e9eba1ef2e1b1ddbf7981fe54706a982be82c18b0ea2c7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26941. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present KinyaEmbed, the first dedicated sentence embedding model for Kinyarwanda, a morphologically rich Bantu language spoken by over 12 million people in Rwanda. Existing multilingual embedding models such as LaBSE, mE5-large, and OpenAI text-embedding-3-large perform poorly on Kinyarwanda due to severe under-representation in their pre-training corpora. KinyaEmbed is built on KinyaBERT-large and trained via a four-stage curriculum using MultipleNegativesRankingLoss (MNRL): Stage 1 leverages ~18,000 paraphrase pairs from the Official Gazette of Rwanda with three temperature scales; Stage 2 fine-tunes on 715 NLLB-translated MNLI triplets for entailment structure; Stage 3 aligns representations using English-Kinyarwanda OPUS-100 translation pairs; Stage 4 refines with 2,936 high-quality pairs filtered from KinyaCOMET at quality threshold 0.8. We evaluate on SemRel2024-rw and introduce Wiki-RW-STS, a new contamination-free Kinyarwanda STS benchmark of 300 pairs derived from Kinyarwanda Wikipedia. A seven-checkpoint ensemble (all5+23A*2, with the final stage double-weighted) achieves Spearman \r{ho}=0.7298 on SemRel2024-rw, surpassing mE5-large by 20.9% and OpenAI text-embedding-3-large by 41.0%. KinyaEmbed also achieves the best document clustering silhouette score (0.2146) across all evaluated models. All checkpoints, the KinyaCOMET filtered pairs, and the Wiki-RW-STS benchmark are publicly available.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.26941 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T15:15:18.078Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).