Are Word Embedding Methods Stable and Should We Care About It?

no code implementations • 17 Apr 2021 • Angana Borah, Manash Pratim Barman, Amit Awekar

A representation learning method is considered stable if it consistently generates similar representation of the given data across multiple runs.

Clustering Fairness +4

Decoding the Style and Bias of Song Lyrics

1 code implementation • 17 Jul 2019 • Manash Pratim Barman, Amit Awekar, Sambhav Kothari

We focus on two aspects: style and biases of song lyrics.