Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
XLNet
open-in-new
<p>The XLNet was an autoregressive <a href="/facts/Transformer_(deep_learning_architecture)/cDbjx6a8">Transformer</a> designed as an improvement over <a href="/facts/BERT_(language_model)/rDSueM4E">BERT</a>, with 340M parameters and trained on 33 billion words. It was released on 19 June 2019, under the <a href="/facts/Apache_License/5AeIjas8">Apache 2.0</a> license. It achieved state-of-the-art results on a variety of natural language processing tasks, including language modeling, question answering, and natural language inference. </p>