sent_debias
EthicML
sent_debias | EthicML | |
---|---|---|
1 | 1 | |
55 | 24 | |
- | - | |
0.0 | 9.3 | |
over 1 year ago | 1 day ago | |
Python | Python | |
MIT License | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
sent_debias
-
academic ethics issues in NLP
following on from the above, to what extent should we trust big models and the built in biases that they learn from huge scraped datasets? Many current SOTA trends for doing few shot learning on nlp tasks involve fine tuning existing large language models. There are lots of interesting research is going on around understanding and removing these biases like this paper from Liang and Li @ ACL2020. A related point is explainability - again some interesting work going on around things like rationale generation this now somewhat old paper by Lei et al 2016 gives some good context
EthicML
-
[R] An overview of some available Fairness Frameworks & Packages
These are all great tools. I found though that there wasn't one package with the flexibility of what we needed in my research group for work in this area, so we wrote EthicML. Some of you may also find it useful too.
What are some alternatives?
responsible-ai-toolbox - Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.
DALEX - moDel Agnostic Language for Exploration and eXplanation
Activeloop Hub - Data Lake for Deep Learning. Build, manage, query, version, & visualize datasets. Stream data real-time to PyTorch/TensorFlow. https://activeloop.ai [Moved to: https://github.com/activeloopai/deeplake]
pygod - A Python Library for Graph Outlier Detection (Anomaly Detection)
fairlearn - A Python package to assess and improve fairness of machine learning models.
verifyml - Open-source toolkit to help companies implement responsible AI workflows.
AIF360 - A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.