Papers
arxiv:1805.12282
On the Impact of Various Types of Noise on Neural Machine Translation
Published on May 31, 2018
Authors:
Abstract
Neural machine translation systems exhibit greater vulnerability to various noise types in parallel training data compared to statistical models, with some noise types causing models to default to input copying behavior.
AI-generated summary
We examine how various types of noise in the parallel training data impact the quality of neural machine translation systems. We create five types of artificial noise and analyze how they degrade performance in neural and statistical machine translation. We find that neural models are generally more harmed by noise than statistical models. For one especially egregious type of noise they learn to just copy the input sentence.
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/1805.12282 in a model README.md to link it from this page.
Datasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/1805.12282 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.