Log In Sign Up

Long-Short Term Masking Transformer: A Simple but Effective Baseline for Document-level Neural Machine Translation

by   Pei Zhang, et al.

Many document-level neural machine translation (NMT) systems have explored the utility of context-aware architecture, usually requiring an increasing number of parameters and computational complexity. However, few attention is paid to the baseline model. In this paper, we research extensively the pros and cons of the standard transformer in document-level translation, and find that the auto-regressive property can simultaneously bring both the advantage of the consistency and the disadvantage of error accumulation. Therefore, we propose a surprisingly simple long-short term masking self-attention on top of the standard transformer to both effectively capture the long-range dependence and reduce the propagation of errors. We examine our approach on the two publicly available document-level datasets. We can achieve a strong result in BLEU and capture discourse phenomena.


Document-Level Neural Machine Translation with Hierarchical Attention Networks

Neural Machine Translation (NMT) can be improved by including document-l...

Document-level Neural Machine Translation with Document Embeddings

Standard neural machine translation (NMT) is on the assumption of docume...

Diving Deep into Context-Aware Neural Machine Translation

Context-aware neural machine translation (NMT) is a promising direction ...

When and Why is Document-level Context Useful in Neural Machine Translation?

Document-level context has received lots of attention for compensating n...

Improving the Transformer Translation Model with Document-Level Context

Although the Transformer translation model (Vaswani et al., 2017) has ac...

Attention-Aware Inference for Neural Abstractive Summarization

Inspired by Google's Neural Machine Translation (NMT) <cit.> that models...