mlsanityData to 14 Oct 2026

Very Low Resource Sentence Alignment: Luhya and Swahili

arXiv 2211.00046 ↗First posted 31 Oct 2022cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 11 of its 28 references that are in the map. First posted on arXiv 31 Oct 2022.

Builds on

11 of 28 references.

References · 11

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  4. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  5. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
  6. 2019WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipediacited by 223
  7. 2019Improving Multilingual Sentence Embedding using Bi-directional Dual Encoder with Additive Margin Softmaxcited by 58
  8. 2017Learning Joint Multilingual Sentence Representations with Neural Machine Translationcited by 52
  9. 2022Bitext Mining Using Distilled Sentence Representations for Low-Resource Languagescited by 48
  10. 2018Effective Parallel Corpus Mining using Bilingual Sentence Embeddingscited by 39
  11. 2018Filtering and Mining Parallel Data in a Joint Multilingual Spacecited by 32

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 2.

6 papers.

  1. 2024Voices Unheard: NLP Resources and Models for Yor`ub'a Regional Dialectscited by 11
  2. 2024State of NLP in Kenya: A Surveycited by 7
  3. 2023Low-resource Bilingual Dialect Lexicon Induction with Large Language Modelscited by 2
  4. 2025FUSE : A Ridge and Random Forest-Based Metric for Evaluating MT in Indigenous Languagescited by 0
  5. 2026Cross-Lingual Transfer for Machine Translation in Turkic Languagescited by 0
  6. 2026Low resource cross-modal alignment using HGNN to enhance speech representationcited by 0