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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSentenceTranslationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MUNIChus: Multilingual News Image Captioning Benchmark
The goal of news image captioning is to generate captions by integrating news article content with corresponding images, highlighting the relationship between textual context and visual elements. The majority of research…
Image CaptioningExtractive Summarization of Long Documents by Combining Global and Local Context
In this paper, we propose a novel neural single document extractive summarization model for long documents, incorporating both the global context of the whole document and the local context within the current topic. We e…
Extractive SummarizationText SummarizationGlobal Attention for Name Tagging
Many name tagging approaches use local contextual information with much success, but fail when the local context is ambiguous or limited. We present a new framework to improve name tagging by utilizing local, document-le…
Generating Uncontextualized and Contextualized Questions for Document-Level Event Argument Extraction
This paper presents multiple question generation strategies for document-level event argument extraction. These strategies do not require human involvement and result in uncontextualized questions as well as contextualiz…
Event Argument ExtractionQuestion GenerationQuestion-GenerationDocument-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling
Document-level relation extraction (RE) poses new challenges compared to its sentence-level counterpart. One document commonly contains multiple entity pairs, and one entity pair occurs multiple times in the document ass…
Document-level Relation ExtractionMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONRelation+2