(Upcoming) An Interactive Visual Demo of Bias Mitigation Techniques for Word Representations
Talk, NeurIPS 2021, Virtual
TBD
Talks and presentations
(Upcoming) Exploring the topology of fine-tuned language models
Talk, Michigan State University, Michigan (Virtual)
TBD
A Visual Tour of Bias Mitigation Techniques for Word Representations
Talk, KDD 2021, Singapore (Virtual)
Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this tutorial, we will review a collection of state-of-the-art debiasing techniques. To aid this, we provide an open source web-based visualization tool and offer hands-on experience in exploring the effects of these debiasing techniques on the geometry of high-dimensional word vectors. To help understand how various debiasing techniques change the underlying geometry, we decompose each technique into interpretable sequences of primitive operations and study their effect on the word vectors using dimensionality reduction and interactive visual exploration.
A Visual Tour of Bias Mitigation Techniques for Word Representations
Talk, AAAI 2021, Virtual
Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this tutorial, we will review a collection of state-of-the-art debiasing techniques. To aid this, we provide an open source web-based visualization tool and offer hands-on experience in exploring the effects of these debiasing techniques on the geometry of high-dimensional word vectors. To help understand how various debiasing techniques change the underlying geometry, we decompose each technique into interpretable sequences of primitive operations and study their effect on the word vectors using dimensionality reduction and interactive visual exploration.