Phrase-Based Attentions

09/30/2018
by   Phi Xuan Nguyen, et al.
0

Most state-of-the-art neural machine translation systems, despite being different in architectural skeletons (e.g. recurrence, convolutional), share an indispensable feature: the Attention. However, most existing attention methods are token-based and ignore the importance of phrasal alignments, the key ingredient for the success of phrase-based statistical machine translation. In this paper, we propose novel phrase-based attention methods to model n-grams of tokens as attention entities. We incorporate our phrase-based attentions into the recently proposed Transformer network, and demonstrate that our approach yields improvements of 1.3 BLEU for English-to-German and 0.5 BLEU for German-to-English translation tasks on WMT newstest2014 using WMT'16 training data.

READ FULL TEXT

page 8

page 11

page 13

research
06/17/2017

Towards Neural Phrase-based Machine Translation

In this paper, we present Neural Phrase-based Machine Translation (NPMT)...
research
05/16/2016

The AMU-UEDIN Submission to the WMT16 News Translation Task: Attention-based NMT Models as Feature Functions in Phrase-based SMT

This paper describes the AMU-UEDIN submissions to the WMT 2016 shared ta...
research
10/20/2016

Iterative Refinement for Machine Translation

Existing machine translation decoding algorithms generate translations i...
research
07/10/2020

Pragmatic information in translation: a corpus-based study of tense and mood in English and German

Grammatical tense and mood are important linguistic phenomena to conside...
research
03/09/2015

Context-Dependent Translation Selection Using Convolutional Neural Network

We propose a novel method for translation selection in statistical machi...
research
02/19/2020

Tree-structured Attention with Hierarchical Accumulation

Incorporating hierarchical structures like constituency trees has been s...
research
06/25/2020

Learning Source Phrase Representations for Neural Machine Translation

The Transformer translation model (Vaswani et al., 2017) based on a mult...

Please sign up or login with your details

Forgot password? Click here to reset