DeepAI AI Chat
Log In Sign Up

The Geometry of Distributed Representations for Better Alignment, Attenuated Bias, and Improved Interpretability

by   Sunipa Dev, et al.

High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of interpretability, with efficient distributed representations coming at the cost of the loss of feature to dimension mapping. This implies that there is obfuscation in the way concepts are captured in these embedding spaces. Its effects are seen in many representations and tasks, one particularly problematic one being in language representations where the societal biases, learned from underlying data, are captured and occluded in unknown dimensions and subspaces. As a result, invalid associations (such as different races and their association with a polar notion of good versus bad) are made and propagated by the representations, leading to unfair outcomes in different tasks where they are used. This work addresses some of these problems pertaining to the transparency and interpretability of such representations. A primary focus is the detection, quantification, and mitigation of socially biased associations in language representation.


page 1

page 2

page 3

page 4


Socially Aware Bias Measurements for Hindi Language Representations

Language representations are an efficient tool used across NLP, but they...

The Lifecycle of "Facts": A Survey of Social Bias in Knowledge Graphs

Knowledge graphs are increasingly used in a plethora of downstream tasks...

"I know it when I see it". Visualization and Intuitive Interpretability

Most research on the interpretability of machine learning systems focuse...

Interpretable Privacy Preservation of Text Representations Using Vector Steganography

Contextual word representations generated by language models (LMs) learn...

Challenges in Automated Debiasing for Toxic Language Detection

Biased associations have been a challenge in the development of classifi...

Bio-inspired data mining: Treating malware signatures as biosequences

The application of machine learning to bioinformatics problems is well e...