mlsanityData to 7 Oct 2026

Simulated Multiple Reference Training Improves Low-Resource Machine Translation

arXiv 2004.14524 ↗First posted 30 Apr 2020cs.CLcited by 22

Not on the map. Why?

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.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 5; 2023: 8; 2024: 5; 2025: 0; 2026: 1.

22 papers.

Sort:

By area:

  1. 2022BRIO: Bringing Order to Abstractive Summarizationcited by 161
  2. 2021Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translationcited by 27
  3. 2022Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translationcited by 13
  4. 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
  5. 2023Not All Metrics Are Guilty: Improving NLG Evaluation by Diversifying Referencescited by 11
  6. 2023Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systemscited by 10
  7. 2024To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translationcited by 10
  8. 2023Data Augmentation for Code Translation with Comparable Corpora and Multiple Referencescited by 9
  9. 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
  10. 2024Quality and Quantity of Machine Translation References for Automatic Metricscited by 7
  11. 2021When Word Embeddings Become Endangeredcited by 6
  12. 2023Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Modelscited by 6
10 more
  1. 2023Target-Side Augmentation for Document-Level Machine Translationcited by 5
  2. 2023Measuring Sentiment Bias in Machine Translationcited by 5
  3. 2023On-the-Fly Fusion of Large Language Models and Machine Translationcited by 5
  4. 2021Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinementcited by 4
  5. 2022ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translationcited by 4
  6. 2024Learning from Many Voices: Literary MT Using Multi-Reference Human and Synthetic Datacited by 3
  7. 2022Text Summarization with Oracle Expectationcited by 1
  8. 2024Diverse Sign Language Translationcited by 1
  9. 2026Ancient Greek to Modern Greek Machine Translation: A Novel Benchmark and Fine-Tuning Experiments on LLMs and NMT Modelscited by 1
  10. 2022Machine Translation Robustness to Natural Asemantic Variationcited by 0