Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back-Translation

By Zhenhao Li, Lucia Specia. 2019

45 citations recorded by the source corpus.

Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of “domain” adaption to noise. The recently created Machine Translation on Noisy Text task corpus provides noisy-clean parallel data for a few language pairs, but this data is very limited in size and diversity. The state-of-the-art approaches are heavily dependent on large volumes of back-translated data. This paper has two main contributions: Firstly, we propose new data augmentation methods to extend limited noisy data and further improve NMT robustness to noise while keeping the models small. Secondly, we explore the effect of utilizing noise from external data in the form of speech transcripts and show that it could help robustness.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

A Survey of Data Augmentation Approaches for NLP (2021, background): “Sugiyama and Yoshinaga (2019) Investigate effectiveness of DA by backtranslation for context-aware NMT. Li and Specia (2019) Present DA methods to improve NMT robustness to noise while keeping models small, and explore the use of noise from external data (speech transcripts).”
ReCode: Robustness Evaluation of Code Generation Models (2022, methodology): “It is a common method for data augmentation in generating sentence variances with the same semantics (Li and Specia, 2019; Sugiyama and Yoshinaga, 2019).”
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation (2021, background): “Thus, our transform only applies to the sentence that has an even number of revertible adjectives or adverbs.”
A Wrong Answer or a Wrong Question? An Intricate Relationship between Question Reformulation and Answer Selection in Conversational Question Answering (2020, background): “Several recent research studies reported that stateof-the-art machine learning models lack in robustness across several NLP tasks (Li and Specia, 2019; Zeng et al., 2019).”