Papers with language model backbone replacement problem

1 papers
FaLA: Fast Linear Adaptation for Replacing Backbone Models on Edge Devices (2023.findings-emnlp)

Copied to clipboard

Challenge: Current NLP models heavily rely on pre-trained models, such as BERT and RoBERTa.
Approach: They propose a lightweight method for personalized NLP classification tasks post-backbone replacement using a personalized matrix calculated from documents corresponding to users' old and new backbones.
Outcome: The proposed method achieves over 1000 times computation reduction in Flops for backpropagation and brings the user-specific initialization for personal matrix yielding significant performance boost compared with popular transfer learning methods.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations