@inproceedings{4b4b58d579b5451198adb90d9207fe2d,
title = "On the properties of neural machine translation: Encoder–decoder approaches",
abstract = "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 newly proposed gated recursive convolutional neural network. We show that the neural machine translation performs relatively well on short sentences without unknown words, but its performance degrades rapidly as the length of the sentence and the number of unknown words increase. Furthermore, we find that the proposed gated recursive convolutional network learns a grammatical structure of a sentence automatically.",
author = "Kyunghyun Cho and {van Merri{\"e}nboer}, Bart and Dzmitry Bahdanau and Yoshua Bengio",
note = "Funding Information: The authors would like to acknowledge the support of the following agencies for research funding and computing support: NSERC, Calcul Qu{\'e}bec, Compute Canada, the Canada Research Chairs and CIFAR. Publisher Copyright: {\textcopyright} 2014 Association for Computational Linguistics; 8th Workshop on Syntax, Semantics and Structure in Statistical Translation, SSST 2014 ; Conference date: 25-10-2014",
year = "2014",
language = "English (US)",
series = "Proceedings of SSST 2014 - 8th Workshop on Syntax, Semantics and Structure in Statistical Translation",
publisher = "Association for Computational Linguistics (ACL)",
pages = "103--111",
editor = "Dekai Wu and Marine Carpuat and Xavier Carreras and Vecchi, {Eva Maria}",
booktitle = "Proceedings of SSST 2014 - 8th Workshop on Syntax, Semantics and Structure in Statistical Translation",
}