Information Bottleneck gives a more natural path to information selection than autoencoding
Overview
We use the Informaiton Bottleneck Principle for completely unsupervised sentence summarization. We release 2 methods:
BottleSumEx: An extractive approach utilizing pretrained language models. This works right out of the box!
BottleSumSelf: A self-supervised abstractive approach utilizing BottleSumEx for example generation.
Our models are simple to use, leverage advantages of large pretrained language models, and offer an exciting step in unsupervised
NLP with information theory.
