Combining PBSMT and NMT Back-translated Data for Efficient NMT

Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is back-translation (Sennrich et al., 2016), which consists on generating synthetic sentences by translating a set of monolingual, target-language sentences using a Machine Translation (MT) model. Generally, NMT models are used for back-translation. In this work, we analyze the performance of models when the training data is extended with synthetic data using different MT approaches. In particular we investigate back-translated data generated not only by NMT but also by Statistical Machine Translation (SMT) models and combinations of both. The results reveal that the models achieve the best performances when the training set is augmented with back-translated data created by merging different MT approaches.

[1]  Alon Lavie,et al.  METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments , 2005, IEEvaluation@ACL.

[2]  Ralph Weischedel,et al.  A STUDY OF TRANSLATION ERROR RATE WITH TARGETED HUMAN ANNOTATION , 2005 .

[3]  Salim Roukos,et al.  Bleu: a Method for Automatic Evaluation of Machine Translation , 2002, ACL.

[4]  Alexander M. Rush,et al.  OpenNMT: Open-Source Toolkit for Neural Machine Translation , 2017, ACL.

[5]  Marcin Junczys-Dowmunt,et al.  Log-linear Combinations of Monolingual and Bilingual Neural Machine Translation Models for Automatic Post-Editing , 2016, WMT.

[6]  Myle Ott,et al.  Understanding Back-Translation at Scale , 2018, EMNLP.

[7]  Andy Way,et al.  Adaptation of Machine Translation Models with Back-translated Data using Transductive Data Selection Methods , 2019, CICLing.

[8]  Philipp Koehn,et al.  Findings of the 2017 Conference on Machine Translation (WMT17) , 2017, WMT.

[9]  Matteo Negri,et al.  Findings of the WMT 2018 Shared Task on Automatic Post-Editing , 2018, WMT.

[10]  Aljoscha Burchardt,et al.  From Human to Automatic Error Classification for Machine Translation Output , 2011, EAMT.

[11]  Philipp Koehn,et al.  Findings of the 2015 Workshop on Statistical Machine Translation , 2015, WMT@EMNLP.

[12]  Kenneth Heafield,et al.  KenLM: Faster and Smaller Language Model Queries , 2011, WMT@EMNLP.

[13]  Philipp Koehn,et al.  Statistical Significance Tests for Machine Translation Evaluation , 2004, EMNLP.

[14]  Maja Popovic.  Hjerson: An Open Source Tool for Automatic Error Classification of Machine Translation Output , 2011, Prague Bull. Math. Linguistics.

[15]  Marco Turchi,et al.  ESCAPE: a Large-scale Synthetic Corpus for Automatic Post-Editing , 2018, LREC.

[16]  Rico Sennrich,et al.  Neural Machine Translation of Rare Words with Subword Units , 2015, ACL.

[17]  François Yvon,et al.  Using Monolingual Data in Neural Machine Translation: a Systematic Study , 2018, WMT.

[18]  Alon Lavie,et al.  Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability , 2011, ACL.

[19]  Franz Josef Och,et al.  Minimum Error Rate Training in Statistical Machine Translation , 2003, ACL.

[20]  Matthew G. Snover,et al.  A Study of Translation Edit Rate with Targeted Human Annotation , 2006, AMTA.

[21]  Rico Sennrich,et al.  Improving Neural Machine Translation Models with Monolingual Data , 2015, ACL.

[22]  Maja Popovic,et al.  chrF: character n-gram F-score for automatic MT evaluation , 2015, WMT@EMNLP.