Understanding Learning Dynamics Of Language Models with SVCCA
share
Recent work has demonstrated that neural language models encode linguistic structure implicitly in a number of ways. However, existing research has not shed light on the process by which this structure is acquired during training. We use SVCCA as a tool for understanding how a language model is implicitly predicting a variety of word cluster tags. We present experiments suggesting that a single recurrent layer of a language model learns linguistic structure in phases. We find, for example, that a language model naturally stabilizes its representation of part of speech earlier than it learns semantic and topic information.
READ FULL TEXT