NobleBlocks
Public

Efficient Retrieval Optimized Multi-task Learning

Published in arXiv (Cornell University) • Apr 20, 2021
NobleIDNI1P13W33R88S77
Authors:
Hengxin Fun
,
Sunil Gandhi
,
Sujith Ravi

Abstract

Recently, there have been significant advances in neural methods for tackling knowledge-intensive tasks such as open domain question answering (QA). These advances are fueled by combining large pre-trained language models with learnable retrieval of documents. Majority of these models use separate e...

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!