# A Representation Level Analysis of NMT Model Robustness to Grammatical Errors

arXiv: https://arxiv.org/abs/2505.21224 · HTML: https://mlsanity.com/paper/2505.21224/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 59 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [COMET: A Neural Framework for MT Evaluation](https://mlsanity.com/paper/2009.09025/) (2020)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Beyond English-Centric Multilingual Machine Translation](https://mlsanity.com/paper/2010.11125/) (2020)
- [What do you learn from context? Probing for sentence structure in contextualized word representations](https://mlsanity.com/paper/1905.06316/) (2019)
- [Linguistic Knowledge and Transferability of Contextual Representations](https://mlsanity.com/paper/1903.08855/) (2019)
- [What BERT is not: Lessons from a new suite of psycholinguistic diagnostics for language models](https://mlsanity.com/paper/1907.13528/) (2019)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Simple, Scalable Adaptation for Neural Machine Translation](https://mlsanity.com/paper/1909.08478/) (2019)
- [PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts](https://mlsanity.com/paper/2306.04528/) (2023)
- [The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives](https://mlsanity.com/paper/1909.01380/) (2019)
- [Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates](https://mlsanity.com/paper/1911.03167/) (2019)
- [What Happens To BERT Embeddings During Fine-tuning?](https://mlsanity.com/paper/2004.14448/) (2020)
- [On the Impact of Various Types of Noise on Neural Machine Translation](https://mlsanity.com/paper/1805.12282/) (2018)
- [Investigating Multilingual NMT Representations at Scale](https://mlsanity.com/paper/1909.02197/) (2019)
- [It's Morphin' Time! Combating Linguistic Discrimination with Inflectional Perturbations](https://mlsanity.com/paper/2005.04364/) (2020)
- [Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks](https://mlsanity.com/paper/1801.07772/) (2018)
- [Similarity Analysis of Contextual Word Representation Models](https://mlsanity.com/paper/2005.01172/) (2020)
- [Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation](https://mlsanity.com/paper/1902.01509/) (2019)
- [A Closer Look at How Fine-tuning Changes BERT](https://mlsanity.com/paper/2106.14282/) (2021)
- [Navigating the Metrics Maze: Reconciling Score Magnitudes and Accuracies](https://mlsanity.com/paper/2401.06760/) (2024)
- [On the Interplay Between Fine-tuning and Sentence-level Probing for Linguistic Knowledge in Pre-trained Transformers](https://mlsanity.com/paper/2010.02616/) (2020)
- [On the Linguistic Representational Power of Neural Machine Translation Models](https://mlsanity.com/paper/1911.00317/) (2019)
- [How transfer learning impacts linguistic knowledge in deep NLP models?](https://mlsanity.com/paper/2105.15179/) (2021)
- [Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers](https://mlsanity.com/paper/2109.08406/) (2021)
- [Spying on your neighbors: Fine-grained probing of contextual embeddings for information about surrounding words](https://mlsanity.com/paper/2005.01810/) (2020)
- [Fluent Translations from Disfluent Speech in End-to-End Speech Translation](https://mlsanity.com/paper/1906.00556/) (2019)
- [Discovering Salient Neurons in Deep NLP Models](https://mlsanity.com/paper/2206.13288/) (2022)

## Built on by (most cited first, 1 of 1)

- [Cross-Modal Robustness Transfer (CMRT): Training Robust Speech Translation Models Using Adversarial Text](https://mlsanity.com/paper/2602.11933/) (2026)

## Abstract (arXiv)

Understanding robustness is essential for building reliable NLP systems. Unfortunately, in the context of machine translation, previous work mainly focused on documenting robustness failures or improving robustness. In contrast, we study robustness from a model representation perspective by looking at internal model representations of ungrammatical inputs and how they evolve through model layers. For this purpose, we perform Grammatical Error Detection (GED) probing and representational similarity analysis. Our findings indicate that the encoder first detects the grammatical error, then corrects it by moving its representation toward the correct form. To understand what contributes to this process, we turn to the attention mechanism where we identify what we term Robustness Heads. We find that Robustness Heads attend to interpretable linguistic units when responding to grammatical errors, and that when we fine-tune models for robustness, they tend to rely more on Robustness Heads for updating the ungrammatical word representation.