Blog Posts

Introductions

What is BERT?

less than 1 minute read

BERT is a state-of-the-art NLP method trained on a very large dataset of texts—namely, the entirety of English-language Wikipedia (2,500 million words) and a...

Back to Top ↑

Quick Tips

Google Colab Notebook Tips

less than 1 minute read

Here are some tips for running BERT in a Google Colab notebook. If you run into strange error messages, if your model takes forever to train, or if your note...

Back to Top ↑

In-context learning

Watch out for confirmation bias

2 minute read

This afternoon I was at a presentation by the Cornell Digital Humanities Summer Fellows. Afterwards, I was talking analysis of poetic forms, and pulled out m...

Back to Top ↑