mlsanityData to 7 Oct 2026

NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in Low-Resource Languages

arXiv 2511.09537 ↗First posted 12 Nov 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We introduce negative space learning machine translation (NSL-MT), a training method for underresourced languages, that augments limited parallel data with synthetically generated violations of the target language's grammar and explicitly penalizes the model when it assigns high probability to these linguistically invalid outputs. NSL-MT delivers improvements across all baselines we tested, including 3-12% BLEU gains for well-performing models and 56-89% gains for models lacking decent initial support. Furthermore, NSL-MT provides a 5x data efficiency multiplier: training with 1,000 examples matches or exceeds normal training with 5,000 examples. NSL-MT thus provides a data-efficient alternative training method for settings where parallel data is limited.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 12 Nov 2025.

Builds on

18 of 35 references.

References · 18

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  5. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  6. 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
  7. 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
  8. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  9. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 906
  10. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  11. 2019Neural Text Generation with Unlikelihood Trainingcited by 489
  12. 2019Massively Multilingual Neural Machine Translationcited by 246
6 more
  1. 2019Choosing Transfer Languages for Cross-Lingual Learningcited by 143
  2. 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 97
  3. 2020Low-resource Languages: A Review of Past Work and Future Challengescited by 90
  4. 2023Contrastive Preference Learning: Learning from Human Feedback without RLcited by 77
  5. 2022Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfercited by 11
  6. 2020Neural Machine Translation: Challenges, Progress and Futurecited by 10

Built on by

Not cited yet.