Stephen Merity
Stephen Merity
Unknown affiliation
Verified email at smerity.com - Homepage
Title
Cited by
Cited by
Year
Pointer sentinel mixture models
S Merity, C Xiong, J Bradbury, R Socher
arXiv preprint arXiv:1609.07843, 2016
8942016
Regularizing and optimizing LSTM language models
S Merity, NS Keskar, R Socher
arXiv preprint arXiv:1708.02182, 2017
8502017
Dynamic memory networks for visual and textual question answering
C Xiong, S Merity, R Socher
International conference on machine learning, 2397-2406, 2016
6892016
Quasi-recurrent neural networks
J Bradbury, S Merity, C Xiong, R Socher
arXiv preprint arXiv:1611.01576, 2016
3942016
An analysis of neural language modeling at multiple scales
S Merity, NS Keskar, R Socher
arXiv preprint arXiv:1803.08240, 2018
1552018
Accurate argumentative zoning with maximum entropy models
S Merity, T Murphy, JR Curran
Proceedings of the 2009 Workshop on Text and Citation Analysis for Scholarly …, 2009
502009
Dynamic Memory Network
R Socher, A Kumar, O Irsoy, M Iyyer, C Xiong, S Merity, R Paulus
US Patent App. 15/170,884, 2016
382016
Single headed attention rnn: Stop thinking with your head
S Merity
arXiv preprint arXiv:1911.11423, 2019
352019
Revisiting activation regularization for language rnns
S Merity, B McCann, R Socher
arXiv preprint arXiv:1708.01009, 2017
352017
Dynamic Memory Network
R Socher, A Kumar, O Irsoy, M Iyyer, C Xiong, S Merity, R Paulus
US Patent App. 15/221,532, 2017
312017
Quasi-recurrent neural network
J Bradbury, SJ Merity, C Xiong, R Socher
US Patent App. 15/420,710, 2018
292018
Quasi-recurrent neural network based encoder-decoder model
J Bradbury, SJ Merity, C Xiong, R Socher
US Patent App. 15/420,801, 2018
272018
Pointer sentinel mixture architecture
SJ Merity, C Xiong, J Bradbury, R Socher
US Patent 10,565,493, 2020
252020
Domain specific language for generation of recurrent neural network architectures
SJ Merity, R Socher, J Bradbury, C Xiong
US Patent App. 15/953,265, 2018
192018
A flexible approach to automated rnn architecture generation
M Schrimpf, S Merity, J Bradbury, R Socher
arXiv preprint arXiv:1712.07316, 2017
132017
The NUGGET Non-Linear Piecewise Activation
S Merity
SIGBOVIK 2018, 57, 2018
22018
Frontier Pruning for Shift-Reduce CCG Parsing
S Merity, JR Curran
Proceedings of the Australasian Language Technology Association Workshop …, 2011
22011
Integrated Tagging and Pruning via Shift-Reduce CCG Parsing
S Merity
School of Information Technologies The University of Sydney, Australia Nov 7, 2011
22011
Scalable Language Modeling: WikiText-103 on a Single GPU in 12 hours
S Merity, NS Keskar, J Bradbury, R Socher
12018
Quasi-recurrent neural network based encoder-decoder model
J Bradbury, SJ Merity, C Xiong, R Socher
US Patent App. 17/122,894, 2021
2021
The system can't perform the operation now. Try again later.
Articles 1–20