paper-with-me

Papers

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

2025-11-12 · Mamadou K. Keita, Christopher Homan, Huy Le 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.

📄 PDF Abstract BibTeX arXiv:2511.09537

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation

Similar Papers 제목 키워드 기반

Semantically-Informed Syntactic Machine Translation: A Tree-Grafting Approach

2014-09-24 · Kathryn Baker, Michael Bloodgood, Chris Callison-Burch, Bonnie J. Dorr 외

We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language tr…

Machine TranslationTranslation

Morphological and Language-Agnostic Word Segmentation for NMT

2018-06-14 · Dominik Macháček, Jonáš Vidra, Ondřej Bojar

The state of the art of handling rich morphology in neural machine translation (NMT) is to break word forms into subword units, so that the overall vocabulary size of these units fits the practical limits given by the NM…

GPUMachine TranslationNMTTranslation

Sign Language Machine Translation and the Sign Language Lexicon: A Linguistically Informed Approach

2022-09-01 · AMTA 2022 9 · Irene Murtagh, Víctor Ubieto Nogales, Josep Blat

Natural language processing and the machine translation of spoken language (speech/text) has benefitted from significant scientific research and development in re-cent times, rapidly advancing the field. On the other han…

Machine TranslationTranslation

Fine-grained evaluation of Quality Estimation for Machine translation based on a linguistically-motivated Test Suite

2019-10-16 · Avramidis Eleftherios, Vivien Macketanz, Arle Lommel, Hans Uszkoreit

We present an alternative method of evaluating Quality Estimation systems, which is based on a linguistically-motivated Test Suite. We create a test-set consisting of 14 linguistic error categories and we gather for each…

Machine TranslationTranslation

BhashaSetu: A Data-Centric Approach to Low-Resource Machine Translation

2026-05-26 · Param Thakkar, Anushka Yadav, Michael Tiemann, Abhi Mehta 외 arxiv

We present BhashaSetu, a linguistically enriched English--Marathi parallel dataset addressing persistent data limitations in low-resource neural machine translation (NMT). Marathi, spoken by over 95 million people, remai…

Low-Resource Neural Machine Translationparameter-efficient fine-tuning