News for hackers. Stuff that matters.

A comment on The Unreasonable Effectiveness of Deep Feature Extraction. Parent comment

Re:The Unreasonable Effectiveness of Deep Feature Extraction by mlucy on Thursday February 14, 2019 @01:54PM (#19164697)
Definitely. There's been a lot of exciting work recently for text in particular, like https://arxiv.org/pdf/1810.04805.pdf .
[ Parent | on HN ]
Re:The Unreasonable Effectiveness of Deep Feature Extraction by nl on Thursday February 14, 2019 @09:58PM (#19168127)
Or from today, OpenAI's response to BERT: https://blog.openai.com/better-language-models/

Breaks 70% accuracy on the Winograd schema for the first time! (a lazy 7% improvement in performance....)

[ Parent | on HN ]