Where words sit in space
The problem static embeddings cannot solve, and why everything changed after BERT.
1 steps
50 XP
Open without an account
Start the lesson →
Sources
- Mikolov, T. et al. 2013 · Efficient Estimation of Word Representations in Vector Space · ICLR Workshop 2013
- Peters, M. et al. 2018 · Deep Contextualized Word Representations (ELMo) · NAACL 2018
- Devlin, J. et al. 2019 · BERT: Pre-training of Deep Bidirectional Transformers · NAACL 2019
- Ethayarajh, K. 2019 · How Contextual are Contextualized Word Representations? · EMNLP 2019
ML Academy · an interactive machine learning course that runs in your browser ·
All lessons