paper-with-me

Papers

Convolutional Sequence to Sequence Learning

2017-05-08 · ICML 2017 8 · Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to recurrent models, computations over all elements can be fully parallelized during training and optimization is easier since the number of non-linearities is fixed and independent of the input length. Our use of gated linear units eases gradient propagation and we equip each decoder layer with a separate attention module. We outperform the accuracy of the deep LSTM setup of Wu et al. (2016) on both WMT'14 English-German and WMT'14 English-French translation at an order of magnitude faster speed, both on GPU and CPU.

📄 PDF Abstract BibTeX arXiv:1705.03122

Code (37)

facebookresearch/fairseq 공식 구현 pytorch
CKPOON0619/Kaggle2Sigma
DavidHarar/Siamese-Networks-for-name-nickname-similarity
Deeksha96/Im2Latex tf
EdinburghNLP/XSum pytorch
Helsinki-NLP/OpenNMT-py pytorch
IBM/pytorch-seq2seq pytorch
Izecson/saml-nmt mxnet
Izecson/sockeye-1.16.6 tf
Kakoedlinnoeslovo/fairseq tf
MiuGod0126/ConvS2S_Paddle paddle
Nick-Zhao-Engr/Machine-Translation pytorch
OpenNMT/OpenNMT-py pytorch
YizhuLiu/sumlen pytorch
ZurichNLP/sockeye mxnet
albarji/neurowriter tf
alisterta/Persian-text-to-speech tf
awslabs/sockeye mxnet
bcmi220/esc4nmt pytorch
butsugiri/shape pytorch
cove-adml/adml-anon pytorch
facebookresearch/ParlAI pytorch
lucylow/En_francais_si_vous_plait- pytorch
memray/OpenNMT-kpg-release pytorch
midobal/OpenNMT-py pytorch
nrc-cnrc/sockeye-multisource mxnet
oneTimePad/conv-nmt tf
phanideepgampa/IM2LATEX tf
richinkabra/CoVe-BCN pytorch
shashiongithub/XSum pytorch
siyuofzhou/CNNSeqToSeq torch
stefannatu/NLP-Translation-Models tf
thinkwee/DPP_CNN_Summarization pytorch
umeiko/mindspore-seq2seq mindspore
xingniu/sockeye mxnet
yinghao1019/NLP_and_DL_practice pytorch
yinghao1019/NLP_and_DL_practice/blob/master/Conv_seq2seq.ipynb pytorch

Tasks

Bangla Spelling Error CorrectionCPUDecoderGPUImage ClassificationMachine TranslationTranslation

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Convolutional Sequence to Sequence Non-intrusive Load Monitoring

2018-06-06 · Kunjin Chen, Qin Wang, Ziyu He, Kunlong Chen 외

A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consu…

Non-Intrusive Load Monitoring

An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling

2018-03-04 · Shaojie Bai, J. Zico Kolter, Vladlen Koltun

For most deep learning practitioners, sequence modeling is synonymous with recurrent networks. Yet recent results indicate that convolutional architectures can outperform recurrent networks on tasks such as audio synthes…

Audio SynthesisLanguage ModellingMachine TranslationMusic Modeling+3

A Context-aware Convolutional Natural Language Generation model for Dialogue Systems

2018-07-01 · WS 2018 7 · Sourab Mangrulkar, Suhani Shrivastava, Veena Thenkanidiyoor, Dileep Aroor Dinesh

Natural language generation (NLG) is an important component in spoken dialog systems (SDSs). A model for NLG involves sequence to sequence learning. State-of-the-art NLG models are built using recurrent neural network (R…

Machine TranslationSemantic correspondenceSpoken Dialogue SystemsText Generation+1

Comparing Recurrent and Convolutional Architectures for English-Hindi Neural Machine Translation

2017-11-01 · WS 2017 11 · S. Singh, hya, Ritesh Panjwani, Anoop Kunchukuttan 외

In this paper, we empirically compare the two encoder-decoder neural machine translation architectures: convolutional sequence to sequence model (ConvS2S) and recurrent sequence to sequence model (RNNS2S) for English-Hin…

DecoderImage CaptioningLanguage ModelingLanguage Modelling+4

DNA-GCN: Graph convolutional networks for predicting DNA-protein binding

2021-06-02 · Yuhang Guo, Xiao Luo, Liang Chen, Minghua Deng

Predicting DNA-protein binding is an important and classic problem in bioinformatics. Convolutional neural networks have outperformed conventional methods in modeling the sequence specificity of DNA-protein binding. Howe…

Specificity