search

filipmellgren / chomsky_decomp

0 stars 0 forks source link

Extracting information from text #5

Open filipmellgren opened 2 years ago

filipmellgren commented 2 years ago
filipmellgren commented 2 years ago

More on BERT: https://cloud.google.com/ai-platform/training/docs/algorithms/bert-start

filipmellgren commented 2 years ago

D'Alonzo, Tegmark: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0271947

Presents an automated way for measuring media bias.

Nice overview of how to prepare the text data, and useful data sources. Think it can be used to create interesting outcome features to analyze over time.

They put data on Kaggle, https://www.kaggle.com/datasets/tegmark/mediabias

Wonder if they also put a model with pretrained weights on there. If yes, we could just apply it without training which would be nice.