Quantifying the Vanishing Gradient and Long Distance Dependency Problem in Recursive Neural Networks and Recursive LSTMs

Phong Le, Willem Zuidema


Anthology ID:
W16-1610
Volume:
Proceedings of the 1st Workshop on Representation Learning for NLP
Month:
August
Year:
2016
Address:
Berlin, Germany
Editors:
Phil Blunsom, Kyunghyun Cho, Shay Cohen, Edward Grefenstette, Karl Moritz Hermann, Laura Rimell, Jason Weston, Scott Wen-tau Yih
Venue:
RepL4NLP
SIG:
SIGREP
Publisher:
Association for Computational Linguistics
Note:
Pages:
87–93
Language:
URL:
https://aclanthology.org/W16-1610
DOI:
10.18653/v1/W16-1610
Bibkey:
Cite (ACL):
Phong Le and Willem Zuidema. 2016. Quantifying the Vanishing Gradient and Long Distance Dependency Problem in Recursive Neural Networks and Recursive LSTMs. In Proceedings of the 1st Workshop on Representation Learning for NLP, pages 87–93, Berlin, Germany. Association for Computational Linguistics.
Cite (Informal):
Quantifying the Vanishing Gradient and Long Distance Dependency Problem in Recursive Neural Networks and Recursive LSTMs (Le & Zuidema, RepL4NLP 2016)
Copy Citation:
PDF:
https://aclanthology.org/W16-1610.pdf