guangliang-nlp Goto Github PK

adept

Source code and data for ADEPT: A DEbiasing PrompT Framework (AAAI-23).

attend

This repository contains Pytorch code for AttenD (Attention Debiasing), a finetuning method for reducing social biases from transformer-based text encoders (e.g. BERT, RoBERTa, ALBERT, DistilBert, SqueezeBERT) and evaluating both fairness and represnetativeness of the final debiased models.

bert-pytorch

Google AI 2018 BERT pytorch implementation

causalmediationanalysis

Code for the paper "Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias"

collapseregularizer

cse830_hw4

cse847ml

cse847mlhomework

ear

Code associated with the paper "Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists"

evaluate_bias_in_mlm

guangliang-nlp.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

mabel

EMNLP 2022: "MABEL: Attenuating Gender Bias using Textual Entailment Data" https://arxiv.org/abs/2210.14975

optiprompt

NAACL'2021: Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240

pactuning

self-debiasing

This repository contains the code for "Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP".

smil

Pytorch implementation of SMIL: Multimodal Learning with Severely Missing Modality (AAAI 2021)

stereoset

StereoSet: Measuring stereotypical bias in pretrained language models