Summary of Leveraging Ontologies to Document Bias in Data, by Mayra Russo and Maria-esther Vidal
Leveraging Ontologies to Document Bias in Data
by Mayra Russo, Maria-Esther Vidal
First submitted to arxiv on: 29 Jun 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Machine learning systems can amplify biases, emphasizing the importance of understanding ML pipelines’ intrinsic characteristics. The absence of a formal resource describing these pipelines in terms of detected biases highlights the need for a documentation framework that enables awareness of bias existence. To address this gap, we present Doc-BiasO ontology, an integrated vocabulary of fair-ML literature-defined biases and measures. We re-use existing vocabulary on machine learning and AI to foster knowledge sharing and interoperability among researchers, developers, regulators, and others. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning systems can have bad habits that make things worse. To fix this, we need to understand how these systems work better. Right now, there isn’t a good way to describe why some biases happen in machine learning. We want to change that by making an easy-to-use guide that explains different kinds of bias and how they’re measured. This will help people working on machine learning talk about the same things and avoid causing more problems. |
Keywords
» Artificial intelligence » Machine learning
