mlsanityData to 7 Oct 2026

To Diverge or Not to Diverge: A Morphosyntactic Perspective on Machine Translation vs Human Translation

arXiv 2401.01419 ↗First posted 2 Jan 2024cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

We conduct a large-scale fine-grained comparative analysis of machine translations (MT) against human translations (HT) through the lens of morphosyntactic divergence. Across three language pairs and two types of divergence defined as the structural difference between the source and the target, MT is consistently more conservative than HT, with less morphosyntactic diversity, more convergent patterns, and more one-to-one alignments. Through analysis on different decoding algorithms, we attribute this discrepancy to the use of beam search that biases MT towards more convergent patterns. This bias is most amplified when the convergent pattern appears around 50% of the time in training data. Lastly, we show that for a majority of morphosyntactic divergences, their presence in HT is correlated with decreased MT performance, presenting a greater challenge for MT systems.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 41 of its 82 references that are in the map. First posted on arXiv 2 Jan 2024.

Builds on

41 of 82 references.

References · 41

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  5. 2016Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddingscited by 1,304
  6. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  7. 2018Adafactor: Adaptive Learning Rates with Sublinear Memory Costcited by 896
  8. 2016Semantics derived automatically from language corpora contain human-like biasescited by 894
  9. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  10. 2017Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraintscited by 420
  11. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  12. 2017Word Embeddings Quantify 100 Years of Gender and Ethnic Stereotypescited by 251
29 more
  1. 2022Scaling Up Models and Data with textttt5x and textttseqiocited by 187
  2. 2019Facebook FAIR's WMT19 News Translation Task Submissioncited by 179
  3. 2022Prompting PaLM for Translation: Assessing Strategies and Performancecited by 144
  4. 2020Is MAP Decoding All You Need? The Inadequacy of the Mode in Neural Machine Translationcited by 137
  5. 2018Analyzing Uncertainty in Neural Machine Translationcited by 126
  6. 2020BLEU might be Guilty but References are not Innocentcited by 109
  7. 2019Mixture Models for Diverse Machine Translation: Tricks of the Tradecited by 77
  8. 2021Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translationcited by 70
  9. 2016A Simple, Fast Diverse Decoding Algorithm for Neural Generationcited by 58
  10. 2020Explicit Alignment Objectives for Multilingual Bidirectional Encoderscited by 50
  11. 2019Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translationcited by 45
  12. 2019Translationese as a Language in "Multilingual" NMTcited by 36
  13. 2023Do GPTs Produce Less Literal Translations?cited by 30
  14. 2019Post-editese: an Exacerbated Translationesecited by 29
  15. 2020Simulated Multiple Reference Training Improves Low-Resource Machine Translationcited by 22
  16. 2020Detecting Fine-Grained Cross-Lingual Semantic Divergences without Supervision by Learning to Rankcited by 18
  17. 2020Decoding and Diversity in Machine Translationcited by 15
  18. 2019Generating Diverse Translation by Manipulating Multi-Head Attentioncited by 14
  19. 2019The University of Edinburgh's Submissions to the WMT19 News Translation Taskcited by 11
  20. 2020Generating Diverse Translation from Model Distribution with Dropoutcited by 10
  21. 2021Mixup Decoding for Diverse Machine Translationcited by 10
  22. 2018Identifying Semantic Divergences in Parallel Text without Annotationscited by 9
  23. 2020Fine-Grained Analysis of Cross-Linguistic Syntactic Divergencescited by 9
  24. 2019Handling Syntactic Divergence in Low-resource Machine Translationcited by 8
  25. 2020Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translationcited by 7
  26. 2020Target Conditioning for One-to-Many Generationcited by 6
  27. 2022Exploring Diversity in Back Translation for Low-Resource Machine Translationcited by 5
  28. 2023Target-Side Augmentation for Document-Level Machine Translationcited by 5
  29. 2021On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 4.

10 papers.

  1. 2024Benchmarking Linguistic Diversity of Large Language Modelscited by 37
  2. 2024Do Large Language Models Have an English Accent? Evaluating and Improving the Naturalness of Multilingual LLMscited by 19
  3. 2025LLM as a Broken Telephone: Iterative Generation Distorts Informationcited by 12
  4. 2026Language of Thought Shapes Output Diversity in Large Language Modelscited by 3
  5. 2025Losing our Tail, Again: (Un)Natural Selection & Multilingual LLMscited by 1
  6. 2025Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationesecited by 0
  7. 2025Automatic Machine Translation Detection Using a Surrogate Multilingual Translation Modelcited by 0
  8. 2026Dialects of Translationese Shape Language Model Learningcited by 0
  9. 2026Testing the Deliteralization Hypothesis in Human and Machine Translationcited by 0
  10. 2026Narrowing the Horizon: Quantifying Topic Saliency Shifts in Generative Monoculturecited by 0