• DOI:10.18653/v1/W18-3024
Corpus ID: 44111606

LSTMs Exploit Linguistic Attributes of Data

@article{Liu2018LSTMsEL,
  title={LSTMs Exploit Linguistic Attributes of Data},
  author={Nelson F. Liu and Omer Levy and Roy Schwartz and Chenhao Tan and Noah A. Smith},
  journal={ArXiv},
  year={2018},
  volume={abs/1805.11653}
}

Nelson F. Liu, Omer Levy, +2 authors Noah A. Smith

Published 2018

Computer Science

ArXiv

While recurrent neural networks have found success in a variety of natural language processing applications, they are general models of sequential data. [...] Key Method Furthermore, we show that the LSTM learns to solve the memorization task by explicitly using a subset of its neurons to count timesteps in the input. We hypothesize that the patterns and structure in natural language data enable LSTMs to learn by providing approximate ways of reducing loss, but understanding the effect of different training…Expand Abstract

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed