VideoCLIP: Contrastive Pre-Training ForZero-Shot Video-Text Understandingyoutube.com·2 pts·deeplstm·0
Shortformer: Better Language Modeling Using Shorter Inputs (Paper Explained)youtube.com·3 pts·deeplstm·1
Well Read Students Learn Better: On the Important of Pre-Training Compact Modelsyoutu.be·6 pts·deeplstm·0
Question and Answer Test-Train Overlap in Open Domain Question Answering Datayoutu.be·3 pts·deeplstm·0
LinkedIn's New Ranking Model – DeText: A Deep Text Ranking Framework with Bertyoutu.be·6 pts·deeplstm·0
QpenQA State-of-the-Art – Realm: Retrieval-Augmented Language Model Pre-Trainingyoutu.be·3 pts·deeplstm·1
GAN Bert: Generative Adversarial Learning for Text Classification (Explained)youtu.be·3 pts·deeplstm·0
Pre-Training Is (Almost) All You Need: An Application to Commonsense Reasoningyoutu.be·2 pts·deeplstm·0
Revealing Dark Secrets of Bert (Analysis of BERT's Attention Heads) Explainedyoutu.be·2 pts·deeplstm·0