Suman Adhya's Projects
Web
Forked repo of the paper "Contrastive Learning for Neural Topic Model"
CTMKD is a inter-VAE knowledge distillation framework.
CTMNeg introduced negative sampling in Contextualized Topic Model to improve the generated topic quality in terms of topic coherence and topic diversity.
This repository is dedicated to the paper "Evaluating Negative Sampling Approaches for Neural Topic Models".
Implementation of Graph Contrastive Topic Model
This repository is dedicated to the paper "GINopic: Topic Modeling with Graph Isomorphism Network," accepted at NAACL 2024.
PyTorch Implementation for Gromov-Wasserstein Autoencoders (GWAE)
This repository is dedicated to the paper titled "What Does the Indian Parliament Discuss? An Exploratory Analysis of the Question Hour in the Lok Sabha".
Details related to the international travel grants for Indian students.
Semi supervised Topic Modeling using Neural Network
This repository is associated with the paper "Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modeling", accepted at EACL 2023.
Papers on Posterior Collapse
ICLR 2023 - Spherical-Sliced Wasserstein