January 1, 2017Open Access

Incorporating Word Reordering Knowledge into Attention-based Neural Machine Translation

Key Points

Key points are not available for this paper at this time.

Abstract

This paper proposes three distortion models to explicitly incorporate the word reordering knowledge into attention-based Neural Machine Translation (NMT) for further improving translation performance.

AIに質問

Bookmark

View Full Paper

Cite This Study

Zhang et al. (Sun,) studied this question.

synapsesocial.com/papers/6a1c98b5107ed6dc7cc4091d https://doi.org/https://doi.org/10.18653/v1/p17-1140

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Minimum Risk Training for Neural Machine Translation2016 · 404 citations
2Effective Approaches to Attention-based Neural Machine Translation2015 · 8,583 citations
3A Unigram Orientation Model for Statistical Machine Translation2004 · 43 citations
4ADADELTA: An Adaptive Learning Rate Method2012 · 5,532 citations
5Statistical Phrase-Based Translation2003 · 966 citations

AIに質問

Bookmark

View Full Paper