Browse SoTA > Natural Language Processing > Machine Translation > Low-Resource Neural Machine Translation

Low-Resource Neural Machine Translation

8 papers with code · Natural Language Processing
Subtask of Machine Translation

Low-resource machine translation is the task of machine translation on a low-resource language where large data may not be available.

Benchmarks

No evaluation results yet. Help compare methods by submit evaluation metrics.

Greatest papers with code

Transfer Learning for Low-Resource Neural Machine Translation

EMNLP 2016 isi-nlp/Zoph_RNN

Ensembling and unknown word replacement add another 2 Bleu which brings the NMT performance on low-resource machine translation close to a strong syntax based machine translation (SBMT) system, exceeding its performance on one language pair.

LOW-RESOURCE NEURAL MACHINE TRANSLATION TRANSFER LEARNING

Data Augmentation for Low-Resource Neural Machine Translation

ACL 2017 marziehf/DataAugmentationNMT

The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora.

DATA AUGMENTATION LOW-RESOURCE NEURAL MACHINE TRANSLATION

Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation

WS 2019 aizhanti/JaRuNC

This paper proposes a novel multilingual multistage fine-tuning approach for low-resource neural machine translation (NMT), taking a challenging Japanese--Russian pair for benchmarking.

DOMAIN ADAPTATION LOW-RESOURCE NEURAL MACHINE TRANSLATION TRANSFER LEARNING

Language Model Prior for Low-Resource Neural Machine Translation

30 Apr 2020cbaziotis/lm-prior-for-nmt

A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data.

LANGUAGE MODELLING LOW-RESOURCE NEURAL MACHINE TRANSLATION

Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies

ACL 2019 yunsukim86/sockeye-transfer

Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies.

CROSS-LINGUAL TRANSFER LOW-RESOURCE NEURAL MACHINE TRANSLATION TRANSFER LEARNING

Low Resource Neural Machine Translation: A Benchmark for Five African Languages

31 Mar 2020surafelml/Afro-NMT

Recent advents in Neural Machine Translation (NMT) have shown improvements in low-resource language (LRL) translation tasks.

LOW-RESOURCE NEURAL MACHINE TRANSLATION TRANSFER LEARNING

Revisiting Low-Resource Neural Machine Translation: A Case Study

ACL 2019 yuekai146/NMT

It has been shown that the performance of neural machine translation (NMT) drops starkly in low-resource conditions, underperforming phrase-based statistical machine translation (PBSMT) and requiring large amounts of auxiliary data to achieve competitive results.

LOW-RESOURCE NEURAL MACHINE TRANSLATION