Amazing technological breakthrough possible @S-Logix

Office Address

  • #5, First Floor, 4th Street Dr. Subbarayan Nagar Kodambakkam, Chennai-600 024 Landmark : Samiyar Madam
  • +91- 81240 01111

Social List

How Contextual are Contextualized Word Representations Comparing the Geometry of BERT,ELMo,and GPT-2 Embeddings - 2019

How Contextual Are Contextualized Word Representations Comparing The Geometry Of Bert,Elmo,And Gpt-2 Embeddings

Research Area:  Machine Learning


Replacing static word embeddings with contextualized word representations has yielded significant improvements on many NLP tasks. However, just how contextual are the contextualized representations produced by models such as ELMo and BERT? Are there infinitely many context-specific representations for each word, or are words essentially assigned one of a finite number of word-sense representations? For one, we find that the contextualized representations of all words are not isotropic in any layer of the contextualizing model. While representations of the same word in different contexts still have a greater cosine similarity than those of two different words, this self-similarity is much lower in upper layers. This suggests that upper layers of contextualizing models produce more context-specific representations, much like how upper layers of LSTMs produce more task-specific representations. In all layers of ELMo, BERT, and GPT-2, on average, less than 5% of the variance in a words contextualized representations can be explained by a static embedding for that word, providing some justification for the success of contextualized representations.


Author(s) Name:  Kawin Ethayarajh

Journal name:  Computer Science

Conferrence name:  

Publisher name:  arXiv:1909.00512

DOI:  10.48550/arXiv.1909.00512

Volume Information: