# Simulated Multiple Reference Training Improves Low-Resource Machine Translation

arXiv: https://arxiv.org/abs/2004.14524 · HTML: https://mlsanity.com/paper/2004.14524/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 22 of 22)

- [BRIO: Bringing Order to Abstractive Summarization](https://mlsanity.com/paper/2203.16804/) (2022)
- [Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation](https://mlsanity.com/paper/2104.06457/) (2021)
- [Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2204.06812/) (2022)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying References](https://mlsanity.com/paper/2305.15067/) (2023)
- [Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems](https://mlsanity.com/paper/2305.19607/) (2023)
- [To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation](https://mlsanity.com/paper/2401.01419/) (2024)
- [Data Augmentation for Code Translation with Comparable Corpora and Multiple References](https://mlsanity.com/paper/2311.00317/) (2023)
- [Neural Machine Translation for the Indigenous Languages of the Americas: An Introduction](https://mlsanity.com/paper/2306.06804/) (2023)
- [Quality and Quantity of Machine Translation References for Automatic Metrics](https://mlsanity.com/paper/2401.01283/) (2024)
- [When Word Embeddings Become Endangered](https://mlsanity.com/paper/2103.13275/) (2021)
- [Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models](https://mlsanity.com/paper/2310.00840/) (2023)
- [Target-Side Augmentation for Document-Level Machine Translation](https://mlsanity.com/paper/2305.04505/) (2023)
- [Measuring Sentiment Bias in Machine Translation](https://mlsanity.com/paper/2306.07152/) (2023)
- [On-the-Fly Fusion of Large Language Models and Machine Translation](https://mlsanity.com/paper/2311.08306/) (2023)
- [Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinement](https://mlsanity.com/paper/2110.09646/) (2021)
- [ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2212.04262/) (2022)
- [Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Data](https://mlsanity.com/paper/2412.18707/) (2024)
- [Text Summarization with Oracle Expectation](https://mlsanity.com/paper/2209.12714/) (2022)
- [Diverse Sign Language Translation](https://mlsanity.com/paper/2410.19586/) (2024)
- [Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Models](https://mlsanity.com/paper/2605.18504/) (2026)
- [Machine Translation Robustness to Natural Asemantic Variation](https://mlsanity.com/paper/2205.12514/) (2022)

## Abstract (arXiv)

Many valid translations exist for a given sentence, yet machine translation (MT) is trained with a single reference translation, exacerbating data sparsity in low-resource settings. We introduce Simulated Multiple Reference Training (SMRT), a novel MT training method that approximates the full space of possible translations by sampling a paraphrase of the reference sentence from a paraphraser and training the MT model to predict the paraphraser's distribution over possible tokens. We demonstrate the effectiveness of SMRT in low-resource settings when translating to English, with improvements of 1.2 to 7.0 BLEU. We also find SMRT is complementary to back-translation.