An Analysis of Source-Side Grammatical Errors in NMT

05/24/2019
by   Antonios Anastasopoulos, et al.
0

The quality of Neural Machine Translation (NMT) has been shown to significantly degrade when confronted with source-side noise. We present the first large-scale study of state-of-the-art English-to-German NMT on real grammatical noise, by evaluating on several Grammar Correction corpora. We present methods for evaluating NMT robustness without true references, and we use them for extensive analysis of the effects that different grammatical errors have on the NMT output. We also introduce a technique for visualizing the divergence distribution caused by a source-side error, which allows for additional insights.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/19/2018

Neural Machine Translation of Text from Non-Native Speakers

Neural Machine Translation (NMT) systems are known to degrade when confr...
research
11/17/2022

Reducing Hallucinations in Neural Machine Translation with Feature Attribution

Neural conditional language generation models achieve the state-of-the-a...
research
05/25/2020

From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction

A great deal of historical corpora suffer from errors introduced by the ...
research
06/29/2016

Compression of Neural Machine Translation Models via Pruning

Neural Machine Translation (NMT), like many other deep learning domains,...
research
04/29/2020

Adversarial Subword Regularization for Robust Neural Machine Translation

Exposing diverse subword segmentations to neural machine translation (NM...
research
03/11/2017

Massive Exploration of Neural Machine Translation Architectures

Neural Machine Translation (NMT) has shown remarkable progress over the ...
research
04/14/2021

The Curious Case of Hallucinations in Neural Machine Translation

In this work, we study hallucinations in Neural Machine Translation (NMT...

Please sign up or login with your details

Forgot password? Click here to reset