Papers by Michael Gill

1 papers
Conditional Word Embedding and Hypothesis Testing via Bayes-by-Backprop (D18-1)

Copied to clipboard

Challenge: Whether word's meaning varies across contexts has become a major focus of research in recent years.
Approach: They propose a word embedding model that incorporates document covariates to estimate conditional word embeds.
Outcome: The proposed model estimates word embedding distributions based on document covariates . if word embeds are statistically significant, hypothesis tests can be performed .

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