# Rare but Severe Neural Machine Translation Errors Induced by Minimal Deletion: An Empirical Study on Chinese and English

arXiv: https://arxiv.org/abs/2209.02145 · HTML: https://mlsanity.com/paper/2209.02145/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 5 Sep 2022.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Pathologies of Neural Models Make Interpretations Difficult](https://mlsanity.com/paper/1804.07781/) (2018)
- [On Adversarial Examples for Character-Level Neural Machine Translation](https://mlsanity.com/paper/1806.09030/) (2018)
- [On the Impact of Various Types of Noise on Neural Machine Translation](https://mlsanity.com/paper/1805.12282/) (2018)
- [Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation](https://mlsanity.com/paper/2010.10907/) (2020)
- [Adv-BERT: BERT is not robust on misspellings! Generating nature adversarial samples on BERT](https://mlsanity.com/paper/2003.04985/) (2020)
- [Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2208.05309/) (2022)
- [Evaluating Robustness to Input Perturbations for Neural Machine Translation](https://mlsanity.com/paper/2005.00580/) (2020)
- [Revisiting Character-Based Neural Machine Translation with Capacity and Compression](https://mlsanity.com/paper/1808.09943/) (2018)
- [Linguistically Motivated Vocabulary Reduction for Neural Machine Translation from Turkish to English](https://mlsanity.com/paper/1707.09879/) (2017)

## Built on by (most cited first, 3 of 3)

- [Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection](https://mlsanity.com/paper/2301.07779/) (2023)
- [An Interdisciplinary Approach to Human-Centered Machine Translation](https://mlsanity.com/paper/2506.13468/) (2025)
- [Examining Pathological Bias in a Generative Adversarial Network Discriminator: A Case Study on a StyleGAN3 Model](https://mlsanity.com/paper/2402.09786/) (2024)

## Abstract (arXiv)

We examine the inducement of rare but severe errors in English-Chinese and Chinese-English in-domain neural machine translation by minimal deletion of the source text with character-based models. By deleting a single character, we can induce severe translation errors. We categorize these errors and compare the results of deleting single characters and single words. We also examine the effect of training data size on the number and types of pathological cases induced by these minimal perturbations, finding significant variation. We find that deleting a word hurts overall translation score more than deleting a character, but certain errors are more likely to occur when deleting characters, with language direction also influencing the effect.