BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle
We use the Informaiton Bottleneck Principle for completely unsupervised sentence summarization. We release 2 methods:
Our models are simple to use, leverage advantages of large pretrained language models, and offer an exciting step in unsupervised
NLP with information theory.
- 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.
Read the paper!
View some examples!
Available soon on Github!
Get in touch!