NLP Highlights cover image

120 - Evaluation of Text Generation, with Asli Celikyilmaz

NLP Highlights

00:00

The Importance of Factual Consistency Measures in Language Generation

In a recent study, the researchers looked at different ways of evaluating language models beyond perplexity and downstream tasks. They came up with this meta evaluation of factual consistency to see which one works better in which scenarios. And then there's a sensitivity about like how much factual consistency inconsistencies in these in the text that they should be able to measure. The findings are we're going to hopefully some of them soon are incredible.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app