no code implementations • NAACL (TrustNLP) 2021 • Hossein Azarpanah, Mohsen Farhadloo
We show that the extent of revealed biases in word embeddings depends on the descriptive statistics and similarity measures used to measure the bias.
no code implementations • 19 Aug 2019 • Mohsen Farhadloo
In this paper we introduce score embedding, a neural network based model to learn interpretable vector representations for words.