Improving Robustness of Machine Translation with Synthetic Noise

By Vaibhav, Sumeet Singh, Craig Stewart, Graham Neubig. 2019

89 citations recorded by the source corpus.

Modern Machine Translation (MT) systems perform remarkably well on clean, in-domain text. However most of the human generated text, particularly in the realm of social media, is full of typos, slang, dialect, idiolect and other noise which can have a disastrous impact on the accuracy of MT. In this paper we propose methods to enhance the robustness of MT systems by emulating naturally occurring noise in otherwise clean data. Synthesizing noise in this manner we are ultimately able to make a vanilla MT system more resilient to naturally occurring noise, partially mitigating loss in accuracy resulting therefrom.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety, Robustness & Interpretability

In Machine Translation

Citations in the corpus

A Survey of Data Augmentation Approaches for NLP (2021, neutral): “, 2020) × 3 tok Input+Label × SLOT-SUB-LM (Louvan and Magnini, 2020) × 3 tok Input 3 UBT & TBT (Vaibhav et al., 2019) × 3 Depends Input 3 SOFT CONTEXTUAL DA (Gao et al.”
On the use of BERT for Neural Machine Translation (2019, background): “Regarding robustness, several recent studies (Karpukhin et al., 2019; Vaibhav et al., 2019) have tackled robustness issues with data augmentation.”
Sometimes We Want Ungrammatical Translations (2021, background): “Yet some studies have also reported that NMT systems can be surprisingly brittle when presented with out-of-domain data (Luong and Manning, 2015), or when trained with noisy input data containing small orthographic (Sakaguchi et al., 2017; Belinkov and Bisk, 2018; Vaibhav et al., 2019; Niu et al., 2”