Visual Cues and Error Correction for Translation Robustness
Not on the map. Why?
Abstract (arXiv)
Neural Machine Translation models are sensitive to noise in the input texts, such as misspelled words and ungrammatical constructions. Existing robustness techniques generally fail when faced with unseen types of noise and their performance degrades on clean texts. In this paper, we focus on three types of realistic noise that are commonly generated by humans and introduce the idea of visual context to improve translation robustness for noisy texts. In addition, we describe a novel error correction training regime that can be used as an auxiliary task to further improve translation robustness. Experiments on English-French and English-German translation show that both multimodal and error correction components improve model robustness to noisy texts, while still retaining translation quality on clean texts.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 33 of its 56 references that are in the map. First posted on arXiv 12 Mar 2021.
Builds on
33 of 56 references.
References · 33
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
- 2017Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answeringcited by 1,310
- 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
- 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 304
- 2016Multi30K: Multilingual English-German Image Descriptionscited by 250
- 2019Transformers without Tears: Improving the Normalization of Self-Attentioncited by 153
- 2019Robust Neural Machine Translation with Doubly Adversarial Inputscited by 105
- 2018On Adversarial Examples for Character-Level Neural Machine Translationcited by 85
- 2017Findings of the Second Shared Task on Multimodal Machine Translation and Multilingual Image Descriptioncited by 76
- 2020AdvAug: Robust Adversarial Augmentation for Neural Machine Translationcited by 66
21 more
- 2018MTNT: A Testbed for Machine Translation of Noisy Textcited by 54
- 2019Probing the Need for Visual Context in Multimodal Machine Translationcited by 54
- 2019Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translationcited by 52
- 2017Doubly-Attentive Decoder for Multi-modal Neural Machine Translationcited by 46
- 2017Incorporating Global Visual Features into Attention-Based Neural Machine Translationcited by 39
- 2019Improving Robustness of Machine Translation with Synthetic Noisecited by 36
- 2018Towards Robust Neural Machine Translationcited by 35
- 2017Attention Strategies for Multi-Source Sequence-to-Sequence Learningcited by 32
- 2019Distilling Translations with Visual Awarenesscited by 30
- 2019Multimodal Machine Translation through Visuals and Speechcited by 29
- 2018Input Combination Strategies for Multi-Source Transformer Decodercited by 22
- 2019Naver Labs Europe's Systems for the WMT19 Machine Translation Robustness Taskcited by 22
- 2016Multimodal Attention for Neural Machine Translationcited by 19
- 2019Findings of the First Shared Task on Machine Translation Robustnesscited by 17
- 2020Simultaneous Machine Translation with Visual Contextcited by 17
- 2019Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back Translationcited by 16
- 2018Neural Machine Translation of Text from Non-Native Speakerscited by 10
- 2020Towards Multimodal Simultaneous Neural Machine Translationcited by 7
- 2020Revisiting Robust Neural Machine Translation: A Transformer Case Studycited by 7
- 2019Predicting Actions to Help Predict Translationscited by 1
- 2019Transformer-based Cascaded Multimodal Speech Translationcited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.