Papers
arxiv:2511.09537

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

Published on May 5
Authors:
,

Abstract

NSL-MT enhances machine translation for underresourced languages by generating syntactic violations and penalizing invalid outputs, achieving superior performance with reduced data requirements.

AI-generated summary

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.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2511.09537
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2511.09537 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2511.09537 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2511.09537 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.