Difference between revisions of "ALBERT: A Lite BERT for Self-supervised Learning of Language Representations"

From statwiki
Jump to: navigation, search
Line 14: Line 14:
  
 
===Inter-sentence coherence loss===
 
===Inter-sentence coherence loss===
[[File:Classification performance.JPG | center]]
+
[[File:SOPvsNSP.png]]
 
===Removing dropout===
 
===Removing dropout===

Revision as of 18:08, 2 November 2020

Presented by

Maziar Dadbin

Introduction

Motivation

Model details

Factorized embedding parameterization

Cross-layer parameter sharing

Inter-sentence coherence loss

SOPvsNSP.png

Removing dropout