BriefGPT.xyz
May, 2018
LSTMs Exploit Linguistic Attributes of Data
LSTMs Exploit Linguistic Attributes of Data
HTML
PDF
Nelson F. Liu, Omer Levy, Roy Schwartz, Chenhao Tan, Noah A. Smith
TL;DR
研究如何通过自然语言数据训练LSTM模型,并发现这种数据能够帮助LSTM模型更好地记忆并回忆输入的令牌,同时LSTM也会通过某些神经元来计算输入的时间步数。
Abstract
While
recurrent neural networks
have found success in a variety of
natural language processing
applications, they are general models of
sequentia
→