microsoft / biosbiasLinks
Code to reproduce data for Bias in Bios
☆46Updated last year
Alternatives and similar repositories for biosbias
Users that are interested in biosbias are comparing it to the libraries listed below
Sorting:
- ☆89Updated 2 years ago
- To analyze and remove gender bias in coreference resolution systems☆78Updated 3 weeks ago
- ☆39Updated 6 years ago
- Code and test data for "On Measuring Bias in Sentence Encoders", to appear at NAACL 2019.☆55Updated 4 years ago
- StereoSet: Measuring stereotypical bias in pretrained language models☆181Updated 2 years ago
- Learning the Difference that Makes a Difference with Counterfactually-Augmented Data☆170Updated 4 years ago
- Code for the paper "Causal Mediation Analysis for Interpreting Neural NLP: The Case of Gender Bias"☆77Updated 3 years ago
- Learning Gender-Neutral Word Embeddings☆47Updated 5 years ago
- ☆18Updated 4 years ago
- Framework for controlling demographic biases in NLG (using adversarial prompts)☆20Updated last year
- Code for Blodgett et al. 2016, Demographic dialectal variation in social media☆25Updated 5 years ago
- NAACL 2019 (Oral): Code for "Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings"☆40Updated 5 years ago
- ☆133Updated last year
- ☆40Updated last year
- Data for evaluating gender bias in coreference resolution systems.☆76Updated 6 years ago
- A curated list of awesome datasets with human label variation (un-aggregated labels) in Natural Language Processing and Computer Vision, …☆83Updated last year
- ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.☆137Updated 5 months ago
- A Python package to compute HONEST, a score to measure hurtful sentence completions in language models. Published at NAACL 2021.☆21Updated last month
- [ACL 2020] Towards Debiasing Sentence Representations☆66Updated 2 years ago
- [ICML 2021] Towards Understanding and Mitigating Social Biases in Language Models☆61Updated 2 years ago
- ☆25Updated 3 years ago
- ☆26Updated 2 years ago
- ☆51Updated 6 years ago
- Find text features that are most related to an outcome, controlling for confounds.☆60Updated 10 months ago
- Dataset + classifier tools to study social perception biases in natural language generation☆69Updated last year
- This repository contains the data and code introduced in the paper "CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Maske…☆119Updated last year
- [ACL 2020] Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation☆27Updated 4 years ago
- ☆39Updated 3 years ago
- Dataset associated with "BOLD: Dataset and Metrics for Measuring Biases in Open-Ended Language Generation" paper☆80Updated 4 years ago
- ☆53Updated 5 years ago