• DOI:10.18653/v1/N19-1329
Corpus ID: 53181926

Understanding Learning Dynamics Of Language Models with SVCCA

@inproceedings{Saphra2019UnderstandingLD,
  title={Understanding Learning Dynamics Of Language Models with SVCCA},
  author={Naomi Saphra and A. Lopez},
  booktitle={NAACL-HLT},
  year={2019}
}

• Naomi Saphra, A. Lopez
• Published in NAACL-HLT 2019
• Computer Science

Research has shown that neural models implicitly encode linguistic features, but there has been no research showing \emph{how} these encodings arise as the models are trained. We present the first study on the learning dynamics of neural language models, using a simple and flexible analysis method called Singular Vector Canonical Correlation Analysis (SVCCA), which enables us to compare learned representations across time and across models, without the need to evaluate directly on annotated… Expand

View on ACL

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed