# Revisiting Low-Resource Neural Machine Translation: A Case Study

arXiv: https://arxiv.org/abs/1905.11901 · HTML: https://mlsanity.com/paper/1905.11901/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 May 2019.

## Built on by (most cited first, 30 of 61)

- [Two-Stream Network for Sign Language Recognition and Translation](https://mlsanity.com/paper/2211.01367/) (2022)
- [Survey of Low-Resource Machine Translation](https://mlsanity.com/paper/2109.00486/) (2021)
- [A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translation](https://mlsanity.com/paper/2203.04287/) (2022)
- [LLMs are Good Sign Language Translators](https://mlsanity.com/paper/2404.00925/) (2024)
- [The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation](https://mlsanity.com/paper/2110.03036/) (2021)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [The Effect of Domain and Diacritics in Yor`ub'a-English Neural Machine Translation](https://mlsanity.com/paper/2103.08647/) (2021)
- [BPE Gets Picky: Efficient Vocabulary Refinement During Tokenizer Training](https://mlsanity.com/paper/2409.04599/) (2024)
- [Why don't people use character-level machine translation?](https://mlsanity.com/paper/2110.08191/) (2021)
- [Examining Scaling and Transfer of Language Model Architectures for Machine Translation](https://mlsanity.com/paper/2202.00528/) (2022)
- [Revisiting End-to-End Speech-to-Text Translation From Scratch](https://mlsanity.com/paper/2206.04571/) (2022)
- [Considerations for meaningful sign language machine translation based on glosses](https://mlsanity.com/paper/2211.15464/) (2022)
- [Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP](https://mlsanity.com/paper/2110.03618/) (2021)
- [Machine Translation from Signed to Spoken Languages: State of the Art and Challenges](https://mlsanity.com/paper/2202.03086/) (2022)
- [Machine Translation between Spoken Languages and Signed Languages Represented in SignWriting](https://mlsanity.com/paper/2210.05404/) (2022)
- [Rethinking Perturbations in Encoder-Decoders for Fast Training](https://mlsanity.com/paper/2104.01853/) (2021)
- [Improving Neural Machine Translation by Bidirectional Training](https://mlsanity.com/paper/2109.07780/) (2021)
- [Few Shot Dialogue State Tracking using Meta-learning](https://mlsanity.com/paper/2101.06779/) (2021)
- [The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2103.11189/) (2021)
- [Scaffold-BPE: Enhancing Byte Pair Encoding for Large Language Models with Simple and Effective Scaffold Token Removal](https://mlsanity.com/paper/2404.17808/) (2024)
- [Hausa Visual Genome: A Dataset for Multi-Modal English to Hausa Machine Translation](https://mlsanity.com/paper/2205.01133/) (2022)
- [GPTs Are Multilingual Annotators for Sequence Generation Tasks](https://mlsanity.com/paper/2402.05512/) (2024)
- [Extended Parallel Corpus for Amharic-English Machine Translation](https://mlsanity.com/paper/2104.03543/) (2021)
- [IndT5: A Text-to-Text Transformer for 10 Indigenous Languages](https://mlsanity.com/paper/2104.07483/) (2021)
- [What changes when you randomly choose BPE merge operations? Not much](https://mlsanity.com/paper/2305.03029/) (2023)
- [An Open-Source Gloss-Based Baseline for Spoken to Signed Language Translation](https://mlsanity.com/paper/2305.17714/) (2023)
- [Machine Translation in the Covid domain: an English-Irish case study for LoResMT 2021](https://mlsanity.com/paper/2403.01196/) (2024)
- [Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Generator-Validator Fine-tuning](https://mlsanity.com/paper/2410.12164/) (2024)
- [Hierarchical Phrase-based Sequence-to-Sequence Learning](https://mlsanity.com/paper/2211.07906/) (2022)
- [On "Scientific Debt" in NLP: A Case for More Rigour in Language Model Pre-Training Research](https://mlsanity.com/paper/2306.02870/) (2023)

## Abstract (arXiv)

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. In this paper, we re-assess the validity of these results, arguing that they are the result of lack of system adaptation to low-resource settings. We discuss some pitfalls to be aware of when training low-resource NMT systems, and recent techniques that have shown to be especially helpful in low-resource settings, resulting in a set of best practices for low-resource NMT. In our experiments on German--English with different amounts of IWSLT14 training data, we show that, without the use of any auxiliary monolingual or multilingual data, an optimized NMT system can outperform PBSMT with far less data than previously claimed. We also apply these techniques to a low-resource Korean-English dataset, surpassing previously reported results by 4 BLEU.