# Naver Labs Europe's Systems for the WMT19 Machine Translation Robustness Task

arXiv: https://arxiv.org/abs/1907.06488 · HTML: https://mlsanity.com/paper/1907.06488/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2019.

## Built on by (most cited first, 23 of 23)

- [The Curious Case of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2104.06683/) (2021)
- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Detecting and Mitigating Hallucinations in Machine Translation: Model Internal Workings Alone Do Well, Sentence Similarity Even Better](https://mlsanity.com/paper/2212.08597/) (2022)
- [NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation](https://mlsanity.com/paper/2112.02721/) (2021)
- [Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation](https://mlsanity.com/paper/2208.05309/) (2022)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection](https://mlsanity.com/paper/2301.07779/) (2023)
- [HalOmi: A Manually Annotated Benchmark for Multilingual Hallucination and Omission Detection in Machine Translation](https://mlsanity.com/paper/2305.11746/) (2023)
- [Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapters](https://mlsanity.com/paper/2110.09574/) (2021)
- [Optimal Transport for Unsupervised Hallucination Detection in Neural Machine Translation](https://mlsanity.com/paper/2212.09631/) (2022)
- [Continual Learning in Multilingual NMT via Language-Specific Embeddings](https://mlsanity.com/paper/2110.10478/) (2021)
- [Document-Level Language Models for Machine Translation](https://mlsanity.com/paper/2310.12303/) (2023)
- [Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions](https://mlsanity.com/paper/2109.05853/) (2021)
- [Generate, Transform, Answer: Question Specific Tool Synthesis for Tabular Data](https://mlsanity.com/paper/2303.10138/) (2023)
- [Efficient Inference for Multilingual Neural Machine Translation](https://mlsanity.com/paper/2109.06679/) (2021)
- [Addressing the Vulnerability of NMT in Input Perturbations](https://mlsanity.com/paper/2104.09810/) (2021)
- [Mitigating Hallucinated Translations in Large Language Models with Hallucination-focused Preference Optimization](https://mlsanity.com/paper/2501.17295/) (2025)
- [UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data Augmentation](https://mlsanity.com/paper/2204.08198/) (2022)
- [Visual Cues and Error Correction for Translation Robustness](https://mlsanity.com/paper/2103.07352/) (2021)
- [DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translation](https://mlsanity.com/paper/2204.09259/) (2022)
- [Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languages](https://mlsanity.com/paper/2308.16075/) (2023)
- [The Functionalizer: Lossless Functional Decomposition for Subword Tokenization](https://mlsanity.com/paper/2609.15991/) (2026)
- [More Than Words: Compositional Tokenization for Efficient Language Models](https://mlsanity.com/paper/2610.05597/) (2026)

## Abstract (arXiv)

This paper describes the systems that we submitted to the WMT19 Machine Translation robustness task. This task aims to improve MT's robustness to noise found on social media, like informal language, spelling mistakes and other orthographic variations. The organizers provide parallel data extracted from a social media website in two language pairs: French-English and Japanese-English (in both translation directions). The goal is to obtain the best scores on unseen test sets from the same source, according to automatic metrics (BLEU) and human evaluation. We proposed one single and one ensemble system for each translation direction. Our ensemble models ranked first in all language pairs, according to BLEU evaluation. We discuss the pre-processing choices that we made, and present our solutions for robustness to noise and domain adaptation.