pith. sign in

arxiv: 1810.10181 · v1 · pith:H4JLFYCNnew · submitted 2018-10-24 · 💻 cs.CL · cs.AI

Exploiting Deep Representations for Neural Machine Translation

classification 💻 cs.CL cs.AI
keywords layerstranslationcapturedecoderencoderinformationmachineneural
0
0 comments X
read the original abstract

Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of encoder and decoder are leveraged in the subsequent process, which misses the opportunity to exploit the useful information embedded in other layers. In this work, we propose to simultaneously expose all of these signals with layer aggregation and multi-layer attention mechanisms. In addition, we introduce an auxiliary regularization term to encourage different layers to capture diverse information. Experimental results on widely-used WMT14 English-German and WMT17 Chinese-English translation data demonstrate the effectiveness and universality of the proposed approach.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts

    cs.CL 2019-06 conditional novelty 6.0

    Gated lexical shortcut connections added to the transformer yield 0.9 BLEU average gains on five WMT directions while lowering the lexical content stored in hidden states.