Machine Translation Robustness to Natural Asemantic Variation

05/25/2022
by   Jacob Bremerman, et al.
0

We introduce and formalize an under-studied linguistic phenomenon we call Natural Asemantic Variation (NAV) and investigate it in the context of Machine Translation (MT) robustness. Standard MT models are shown to be less robust to rarer, nuanced language forms, and current robustness techniques do not account for this kind of perturbation despite their prevalence in "real world" data. Experiment results provide more insight into the nature of NAV and we demonstrate strategies to improve performance on NAV. We also show that NAV robustness can be transferred across languages and fine that synthetic perturbations can achieve some but not all of the benefits of human-generated NAV data.

READ FULL TEXT
research
07/02/2019

Improving Robustness in Real-World Neural Machine Translation Engines

As a commercial provider of machine translation, we are constantly train...
research
02/25/2019

Improving Robustness of Machine Translation with Synthetic Noise

Modern Machine Translation (MT) systems perform consistently well on cle...
research
10/31/2019

Machine Translation of Restaurant Reviews: New Corpus for Domain Adaptation and Robustness

We share a French-English parallel corpus of Foursquare restaurant revie...
research
10/15/2021

Why don't people use character-level machine translation?

We present a literature and empirical survey that critically assesses th...
research
02/16/2023

Evaluating and Improving the Coreference Capabilities of Machine Translation Models

Machine translation (MT) requires a wide range of linguistic capabilitie...
research
05/26/2023

CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation

Neural machine translation (NMT) systems exhibit limited robustness in h...
research
02/05/2019

Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation

We consider the problem of making machine translation more robust to cha...

Please sign up or login with your details

Forgot password? Click here to reset