Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing

05/16/2016
by   Marcin Junczys-Dowmunt, et al.
0

This paper describes the submission of the AMU (Adam Mickiewicz University) team to the Automatic Post-Editing (APE) task of WMT 2016. We explore the application of neural translation models to the APE problem and achieve good results by treating different models as components in a log-linear model, allowing for multiple inputs (the MT-output and the source) that are decoded to the same target language (post-edited translations). A simple string-matching penalty integrated within the log-linear model is used to control for higher faithfulness with regard to the raw machine translation output. To overcome the problem of too little training data, we generate large amounts of artificial data. Our submission improves over the uncorrected baseline on the unseen test set by -3.2% TER and +5.5% BLEU and outperforms any other system submitted to the shared-task by a large margin.

READ FULL TEXT

page 1

page 2

page 3

page 4

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
05/30/2019

Unbabel's Submission to the WMT2019 APE Shared Task: BERT-based Encoder-Decoder for Automatic Post-Editing

This paper describes Unbabel's submission to the WMT2019 APE Shared Task...
research
09/14/2021

Netmarble AI Center's WMT21 Automatic Post-Editing Shared Task Submission

This paper describes Netmarble's submission to WMT21 Automatic Post-Edit...
research
08/10/2015

Feature-based Decipherment for Large Vocabulary Machine Translation

Orthographic similarities across languages provide a strong signal for p...
research
08/16/2019

Improving CAT Tools in the Translation Workflow: New Approaches and Evaluation

This paper describes strategies to improve an existing web-based compute...
research
06/15/2017

Ensembling Factored Neural Machine Translation Models for Automatic Post-Editing and Quality Estimation

This work presents a novel approach to Automatic Post-Editing (APE) and ...
research
04/29/2020

Learning Non-Monotonic Automatic Post-Editing of Translations from Human Orderings

Recent research in neural machine translation has explored flexible gene...

Please sign up or login with your details

Forgot password? Click here to reset