activity
20192022
most citedA Discrete Variational Recurrent Topic Model without the Reparametrization Trick

14 citations · 15 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG2022

RevUp: Revise and Update Information Bottleneck for Event Representation

Mehdi Rezaee, Francis Ferraro

The existence of external (``side'') semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be no…

cs.CL2021★ 1 cited

Discriminative and Generative Transformer-based Models For Situation Entity Classification

Mehdi Rezaee, Kasra Darvish, Gaoussou Youssouf Kebe +1

We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode senten…

cs.LG2020★ 14 cited

A Discrete Variational Recurrent Topic Model without the Reparametrization Trick

Mehdi Rezaee, Francis Ferraro

We show how to learn a neural topic model with discrete random variables---one that explicitly models each word's assigned topic---using neural variational inference that does not…

cs.LG2020

Event Representation with Sequential, Semi-Supervised Discrete Variables

Mehdi Rezaee, Francis Ferraro

Within the context of event modeling and understanding, we propose a new method for neural sequence modeling that takes partially-observed sequences of discrete, external knowledge…

math.OC2019

A Survey on Compressive Sensing: Classical Results and Recent Advancements

Ahmad Mousavi, Mehdi Rezaee, Ramin Ayanzadeh

Recovering sparse signals from linear measurements has demonstrated outstanding utility in a vast variety of real-world applications. Compressive sensing is the topic that studies…