Papers with ProdLDA

3 papers
Do Neural Topic Models Really Need Dropout? Analysis of the Effect of Dropout in Topic Modeling (2023.eacl-main)

Copied to clipboard

Challenge: Dropout is a regularization trick used to resolve overfitting in large feedforward neural networks, but there is nil analysis of it for unsupervised models and in particular, VAE-based neural topic models.
Approach: They propose to use dropout to solve overfitting problems in unsupervised neural topic models by stochastically dropping out the activation of neurons to prevent complex co-adaptations of feature vectors.
Outcome: The proposed class of neural topic models can be used to improve the quality and predictive performance of the generated topics.
Reinforcement Learning for Topic Models (2023.findings-acl)

Copied to clipboard

Challenge: Topic modeling is a method to extract information from documents by grouping topics into topics and linking them with words describing them.
Approach: They propose to replace the variational autoencoder with a continuous action space reinforcement learning policy and modify the neural network architecture to weight the ELBO loss.
Outcome: The proposed model outperforms all other unsupervised models and performs on par with or better than most models using supervised labeling and contrastive learning.
Exploring Neural Topic Modeling on a Classical Latin Corpus (2024.lrec-main)

Copied to clipboard

Challenge: Using topic modeling, it is possible to study Latin literature through methods and tools that support distant reading.
Approach: They propose to use topic modeling to investigate thematic distribution of Latin corpus . they train, optimize and compare two neural models to evaluate which performs better .
Outcome: The proposed model is compared with two neural models with a Classical Latin corpus and shows that it is coherent and interpretable.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations