On the Properties of Neural Machine Translation: Encoder-Decoder Approaches

@article{Cho2014OnTP,
  title={On the Properties of Neural Machine Translation: Encoder-Decoder Approaches},
  author={Kyunghyun Cho and Bart van Merrienboer and Dzmitry Bahdanau and Yoshua Bengio},
  journal={ArXiv},
  year={2014},
  volume={abs/1409.1259}
}
Neural machine translation is a relatively new approach to statistical machine translation based purely on neural networks. The neural machine translation models often consist of an encoder and a decoder. The encoder extracts a fixed-length representation from a variable-length input sentence, and the decoder generates a correct translation from this representation. In this paper, we focus on analyzing the properties of the neural machine translation using two models; RNN Encoder--Decoder and a… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 1,217 CITATIONS, ESTIMATED 85% COVERAGE

Cooperative Denoising for Distantly Supervised Relation Extraction

  • COLING
  • 2018
VIEW 11 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Learnable pooling with Context Gating for video classification

VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Copy this Sentence

VIEW 14 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Deep Learning for Multi-Class Identification From Domestic Violence Online Posts

  • IEEE Access
  • 2019
VIEW 20 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Recurrent Neural Networks For Accurate RSSI Indoor Localization

VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

SeqViews2SeqLabels: Learning 3D Global Features via Aggregating Sequential Views by RNN With Attention

  • IEEE Transactions on Image Processing
  • 2019
VIEW 6 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

User-Oriented Paraphrase Generation With Keywords Controlled Network

Daojian Zeng, Haoran Zhang, Lingyun Xiang, Jin Wang, Guoliang Ji
  • IEEE Access
  • 2019
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 298 Highly Influenced Citations

  • Averaged 330 Citations per year over the last 3 years