DeepAI AI Chat
Log In Sign Up

A Shared Attention Mechanism for Interpretation of Neural Automatic Post-Editing Systems

by   Inigo Jauregi Unanue, et al.
University of Technology Sydney
Capital Markets CRC Limited

Automatic post-editing (APE) systems aim to correct the systematic errors made by machine translators. In this paper, we propose a neural APE system that encodes the source (src) and machine translated (mt) sentences with two separate encoders, but leverages a shared attention mechanism to better understand how the two inputs contribute to the generation of the post-edited (pe) sentences. Our empirical observations have showed that when the mt is incorrect, the attention shifts weight toward tokens in the src sentence to properly edit the incorrect translation. The model has been trained and evaluated on the official data from the WMT16 and WMT17 APE IT domain English-German shared tasks. Additionally, we have used the extra 500K artificial data provided by the shared task. Our system has been able to reproduce the accuracies of systems trained with the same data, while at the same time providing better interpretability.


LIG-CRIStAL System for the WMT17 Automatic Post-Editing Task

This paper presents the LIG-CRIStAL submission to the shared Automatic P...

An Exploration of Neural Sequence-to-Sequence Architectures for Automatic Post-Editing

In this work, we explore multiple neural architectures adapted for the t...

eSCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing

Training models for the automatic correction of machine-translated text ...

The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task

This paper presents the JHU-Microsoft joint submission for WMT 2021 qual...

Learning to Copy for Automatic Post-Editing

Automatic post-editing (APE), which aims to correct errors in the output...

The Transference Architecture for Automatic Post-Editing

In automatic post-editing (APE) it makes sense to condition post-editing...

Automatic Post-Editing for Machine Translation

Automatic Post-Editing (APE) aims to correct systematic errors in a mach...