OpenAI achieved state-of-the-art results on multiple language tasks with a general, task-agnostic system combining a Transformer with unsupervised pretraining, and released the system as open source. OpenAI said the results validate combining supervised learning with unsupervised pretraining and expressed hope that they will drive further research on larger and more diverse datasets.
Key Takeaways
OpenAI achieved state-of-the-art results on multiple language tasks with a general,task-agnostic…
and released the system as open source.
OpenAI said the results validate combining supervised learning with unsupervised pretraining and…
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: OpenAI releases language understanding model based on unsupervised pretraining, achieving SOTA results. June 11, 2018. https://new.nat6.net/en/news/kqw3u0zsdrdahfl69kk21gyhw/