22 citations · 33 across the 17 of their papers we have counts for
3 papers · 1 filter
XAM: Interactive Explainability for Authorship Attribution Models
Milad Alshomary, Anisha Bhatnagar, Peter Zeng +3
We present IXAM, an Interactive eXplainability framework for Authorship Attribution Models. Given an authorship attribution (AA) task and an embedding-based AA model, our tool enab…
iBERT: Interpretable Embeddings via Sense Decomposition
Vishal Anand, Milad Alshomary, Kathleen McKeown
We present iBERT (interpretable-BERT), an encoder to produce inherently interpretable and controllable embeddings - designed to modularize and expose the discriminative cues presen…
Layered Insights: Generalizable Analysis of Authorial Style by Leveraging All Transformer Layers
Milad Alshomary, Nikhil Reddy Varimalla, Vishal Anand +2
We propose a new approach for the authorship attribution task that leverages the various linguistic representations learned at different layers of pre-trained transformer-based mod…