English-Czech Systems in WMT19: Document-Level Transformer

07/30/2019

∙

We describe our NMT systems submitted to the WMT19 shared task in English-Czech news translation. Our systems are based on the Transformer model implemented in either Tensor2Tensor (T2T) or Marian framework. We aimed at improving the adequacy and coherence of translated documents by enlarging the context of the source and target. Instead of translating each sentence independently, we split the document into possibly overlapping multi-sentence segments. In case of the T2T implementation, this "document-level"-trained system achieves a +0.6 BLEU improvement (p<0.05) relative to the same system applied on isolated sentences. To assess the potential effect document-level models might have on lexical coherence, we performed a semi-automatic analysis, which revealed only a few sentences improved in this aspect. Thus, we cannot draw any conclusions from this weak evidence.

READ FULL TEXT

English-Czech Systems in WMT19: Document-Level Transformer

Toward Making the Most of Context in Neural Machine Translation

Capturing document context inside sentence-level neural machine translation models with self-training

Split-Correctness in Information Extraction

Big Bidirectional Insertion Representations for Documents

Diverse Pretrained Context Encodings Improve Document Translation

Machine Translation of Mathematical Text

Aspect-augmented Adversarial Networks for Domain Adaptation

English-Czech Systems in WMT19: Document-Level Transformer

Related Research

Toward Making the Most of Context in Neural Machine Translation

Capturing document context inside sentence-level neural machine translation models with self-training

Split-Correctness in Information Extraction

Big Bidirectional Insertion Representations for Documents

Diverse Pretrained Context Encodings Improve Document Translation

Machine Translation of Mathematical Text

Aspect-augmented Adversarial Networks for Domain Adaptation