Papers by Qile Zhu

2 papers
A Batch Normalized Inference Network Keeps the KL Vanishing Away (2020.acl-main)

Copied to clipboard

Challenge: Variational Autoencoder (VAE) is widely used to approximate a model’s posterior on latent variables.
Approach: They propose to let the Kullback–Leibler divergence individual follow a distribution across the whole dataset and analyze that it is sufficient to prevent posterior collapse by keeping the expectation of the KL’s distribution positive.
Outcome: The proposed approach can avoid posterior collapse effectively and efficiently without introducing any new model component or modifying the objective.
GraphBTM: Graph Enhanced Autoencoded Variational Inference for Biterm Topic Model (D18-1)

Copied to clipboard

Challenge: Conventional topic models suffer different problems in different settings.
Approach: They propose a novel way to model word-pairs named biterms in the whole corpus and a Graph Convolutional Networks (GCNs) with residual connections to extract transitive features from biterm.
Outcome: The proposed model generates more coherent topics compared with previous methods.

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