DeepAI AI Chat
Log In Sign Up

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

by   Alexandre Berard, et al.
University Lille 1: Sciences and Technologies
Université Grenoble Alpes

This paper presents the LIG-CRIStAL submission to the shared Automatic Post- Editing task of WMT 2017. We propose two neural post-editing models: a monosource model with a task-specific attention mechanism, which performs particularly well in a low-resource scenario; and a chained architecture which makes use of the source sentence to provide extra context. This latter architecture manages to slightly improve our results when more training data is available. We present and discuss our results on two datasets (en-de and de-en) that are made available for the task.


page 1

page 2

page 3

page 4


MS-UEdin Submission to the WMT2018 APE Shared Task: Dual-Source Transformer for Automatic Post-Editing

This paper describes the Microsoft and University of Edinburgh submissio...

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

Automatic post-editing (APE) systems aim to correct the systematic error...

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

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

UdS Submission for the WMT 19 Automatic Post-Editing Task

In this paper, we describe our submission to the English-German APE shar...

Local Editing in LZ-End Compressed Data

This paper presents an algorithm for the modification of data compressed...

Robustness of edited neural networks

Successful deployment in uncertain, real-world environments requires tha...

Real Differences between OT and CRDT for Co-Editors

OT (Operational Transformation) was invented for supporting real-time co...