Blog posts
-
Wed 24 January 2024
Paper: "Undesirable Biases in NLP: Addressing Challenges of Measurement"
This post is about our paper "Undesirable Biases in NLP: Addressing Challenges of Measurement", published in JAIR.
Developing tools for measuring & mitigating bias is challenging: LM bias is a complex sociocultural phenomenon and we have no access to a ground truth. We voice our concerns about current bias evaluation practices …
Sun 01 January 2023Taking a step back and positioning bias: three considerations
In a previous blog post, I have mentioned some ways to investigate the gender bias of natural language processing (NLP) systems (language models). When discussing the undesirable biases, we often take a mathematical and ‘mechanistic’ approach, where we measure a deviation from a (prescriptive) norm of ideal behavior (e.g …
Thu 14 July 2022The Birth of Bias: A case study on the evolution of gender bias in an English language model
The language model (LM) is an essential building block of current AI systems dealing with natural language, and has proven to be useful in tasks as diverse as sentiment analysis, text generation, translations, and summarizing. These LMs are typically based on neural networks and trained on vast amounts of training …
Fri 01 April 2022PhD Tools: Zotero
Zotero is a free and open source reference manager. I like how polished the software is and the many features/plugins that are available. With the browser extension I can easily capture articles while browsing the internet, with group libraries I can organize and share papers with different research groups …
Wed 02 February 2022How do I know if my language model is gender-biased?
This blog post appeared on the Bias Barometer website
The language model (LM) is an essential building block of current AI systems dealing with natural language, and has proven to be useful in tasks as diverse as sentiment analysis, text generation, translations, and summarizing. These LMs are typically based on …