Papers with preserves language model

1 papers
Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations (2020.coling-main)

Copied to clipboard

Challenge: Prior work identifies a linear gender subspace and removes gender information by eliminating the subspace.
Approach: They propose to use DensRay to obtain interpretable dense subspaces by applying it to attention heads and layers of BERT.
Outcome: The proposed method performs on-par with prior approaches, but is more robust and preserves language model performance better.

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