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

07/01/2018
by   Inigo Jauregi Unanue, et al.
0

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.

READ FULL TEXT
research
07/17/2017

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

This paper presents the LIG-CRIStAL submission to the shared Automatic P...
research
06/13/2017

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

In this work, we explore multiple neural architectures adapted for the t...
research
03/20/2018

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

Training models for the automatic correction of machine-translated text ...
research
07/11/2017

Refining Raw Sentence Representations for Textual Entailment Recognition via Attention

In this paper we present the model used by the team Rivercorners for the...
research
11/09/2019

Learning to Copy for Automatic Post-Editing

Automatic post-editing (APE), which aims to correct errors in the output...
research
10/18/2019

Automatic Post-Editing for Machine Translation

Automatic Post-Editing (APE) aims to correct systematic errors in a mach...
research
06/14/2019

A Simple and Effective Approach to Automatic Post-Editing with Transfer Learning

Automatic post-editing (APE) seeks to automatically refine the output of...

Please sign up or login with your details

Forgot password? Click here to reset