Multi-source transformer with combined losses for automatic post editing

Recent approaches to the Automatic Postediting (APE) of Machine Translation (MT) have shown that best results are obtained by neural multi-source models that correct the raw MT output by also considering information from the corresponding source sentence. To this aim, we present for the first time a neural multi-source APE model based on the Transformer architecture. Moreover, we employ sequence-level loss functions in order to avoid exposure bias during training and to be consistent with the automatic evaluation metrics used for the task. These are the main features of our submissions to the WMT 2018 APE shared task, where we participated both in the PBSMT subtask (i.e. the correction of MT outputs from a phrase-based system) and in the NMT subtask (i.e. the correction of neural outputs). In the first subtask, our system improves over the baseline up to -5.3 TER and +8.23 BLEU points ranking second out of 11 submitted runs. In the second one, characterized by the higher quality of the initial translations, we report lower but statistically significant gains (up to -0.38 TER and +0.8 BLEU), ranking first out of 10 submissions.

[1]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

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

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Yang Liu,et al.  Minimum Risk Training for Neural Machine Translation , 2015, ACL.

[5]  Marcin Junczys-Dowmunt,et al.  The AMU-UEdin Submission to the WMT 2017 Shared Task on Automatic Post-Editing , 2017, WMT.

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

[7]  Karin M. Verspoor,et al.  Findings of the 2016 Conference on Machine Translation , 2016, WMT.

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

[9]  Philipp Koehn,et al.  Empirical Methods for Compound Splitting , 2003, EACL.

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

[11]  Santanu Pal,et al.  Multi-source Neural Automatic Post-Editing: FBK’s participation in the WMT 2017 APE shared task , 2017, WMT.

[12]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[13]  Chris Hokamp,et al.  Ensembling Factored Neural Machine Translation Models for Automatic Post-Editing and Quality Estimation , 2017, WMT.

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

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

[16]  Colin Cherry,et al.  A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU , 2014, WMT@ACL.

[17]  Kevin Knight,et al.  Multi-Source Neural Translation , 2016, NAACL.

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

[19]  Fabienne Braune,et al.  LMU Munich’s Neural Machine Translation Systems for News Articles and Health Information Texts , 2017, WMT.

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

[21]  Marco Turchi,et al.  The FBK Participation in the WMT15 Automatic Post-editing Shared Task , 2015 .

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