Combining Local and Document-Level Context: The LMU Munich Neural Machine Translation System at WMT19

We describe LMU Munich’s machine translation system for English→German translation which was used to participate in the WMT19 shared task on supervised news translation. We specifically participated in the document-level MT track. The system used as a primary submission is a context-aware Transformer capable of both rich modeling of limited contextual information and integration of large-scale document-level context with a less rich representation. We train this model by fine-tuning a big Transformer baseline. Our experimental results show that document-level context provides for large improvements in translation quality, and adding a rich representation of the previous sentence provides a small additional gain.

• Publication year

  2019

• Venue

  Conference on Machine Translation

• Publication date

  Unknown publication date

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/W19-5345
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• The University of Cambridge’s Machine Translation Systems for WMT18

  2018cited by this paper
• Has Machine Translation Achieved Human Parity? A Case for Document-level Evaluation

  2018cited by this paper
• Multi-Domain Neural Machine Translation

  2018cited by this paper
• Coreference and Coherence in Neural Machine Translation: A Study Using Oracle Experiments

  2018influential reference
• Improving the Transformer Translation Model with Document-Level Context

  2018influential reference
• Microsoft’s Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data

  2018cited by this paper
• Achieving Human Parity on Automatic Chinese to English News Translation

  2018cited by this paper
• Context-Aware Neural Machine Translation Learns Anaphora Resolution

  2018influential reference
• Sentence Weighting for Neural Machine Translation Domain Adaptation

  2018cited by this paper
• Document-Level Neural Machine Translation with Hierarchical Attention Networks

  2018influential reference
• Attaining the Unattainable? Reassessing Claims of Human Parity in Neural Machine Translation

  2018cited by this paper
• A Call for Clarity in Reporting BLEU Scores

  2018cited by this paper
• The Sockeye Neural Machine Translation Toolkit at AMTA 2018

  2018cited by this paper
• Does Neural Machine Translation Benefit from Larger Context?

  2017cited by this paper
• Neural Machine Translation with Extended Context

  2017cited by this paper
• Evaluating Discourse Phenomena in Neural Machine Translation

  2017cited by this paper
• Learning to Remember Translation History with a Continuous Cache

  2017cited by this paper
• Exploiting Cross-Sentence Context for Neural Machine Translation

  2017cited by this paper
• Attention is All you Need

  2017influential reference
• Document Context Neural Machine Translation with Memory Networks

  2017cited by this paper
• Multi-Domain Neural Machine Translation through Unsupervised Adaptation

  2017cited by this paper
• Neural Machine Translation Training in a Multi-Domain Scenario

  2017cited by this paper
• Cost Weighting for Neural Machine Translation Domain Adaptation

  2017cited by this paper
• Domain Control for Neural Machine Translation

  2016influential reference
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

  2016cited by this paper
• Fast Domain Adaptation for Neural Machine Translation

  2016cited by this paper
• Neural Machine Translation of Rare Words with Subword Units

  2015cited by this paper
• Improving Neural Machine Translation Models with Monolingual Data

  2015cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper

• Improving Long Context Document-Level Machine Translation

  2023cites this paper
• A Survey on Document-level Neural Machine Translation

  2021cites this paper
• Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey

  2021cites this paper
• Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution

  2021cites this paper
• Addressing Zero-Resource Domains Using Document-Level Context in Neural Machine Translation

  2020cites this paper
• Improving Document-Level Neural Machine Translation with Domain Adaptation

  2020cites this paper
• Findings of the 2019 Conference on Machine Translation (WMT19)

  2019influential citation
• A Survey on Document-level Machine Translation: Methods and Evaluation

  2019cites this paper