DeepAI AI Chat
Log In Sign Up

Robust Neural Machine Translation: Modeling Orthographic and Interpunctual Variation

by   Toms Bergmanis, et al.

Neural machine translation systems typically are trained on curated corpora and break when faced with non-standard orthography or punctuation. Resilience to spelling mistakes and typos, however, is crucial as machine translation systems are used to translate texts of informal origins, such as chat conversations, social media posts and web pages. We propose a simple generative noise model to generate adversarial examples of ten different types. We use these to augment machine translation systems' training data and show that, when tested on noisy data, systems trained using adversarial examples perform almost as well as when translating clean data, while baseline systems' performance drops by 2-3 BLEU points. To measure the robustness and noise invariance of machine translation systems' outputs, we use the average translation edit rate between the translation of the original sentence and its noised variants. Using this measure, we show that systems trained on adversarial examples on average yield 50 data.


page 1

page 2

page 3

page 4


Robust Neural Machine Translation with Doubly Adversarial Inputs

Neural machine translation (NMT) often suffers from the vulnerability to...

On the Impact of Various Types of Noise on Neural Machine Translation

We examine how various types of noise in the parallel training data impa...

Robust Unsupervised Neural Machine Translation with Adversarial Training

Unsupervised neural machine translation (UNMT) has recently attracted gr...

Synthetic and Natural Noise Both Break Neural Machine Translation

Character-based neural machine translation (NMT) models alleviate out-of...

Impact of Corpora Quality on Neural Machine Translation

Large parallel corpora that are automatically obtained from the web, doc...

A Reinforced Generation of Adversarial Samples for Neural Machine Translation

Neural machine translation systems tend to fail on less de-cent inputs d...