Papers by Jon Gillick

2 papers
Please Clap: Modeling Applause in Campaign Speeches (N18-1)

Copied to clipboard

Challenge: a new corpus of speeches from campaign events is used to predict moments of audience applause . lexical features carry the most information, but a variety of features are predictive .
Approach: They propose a corpus of speeches from campaign events in the months leading up to the 2016 election and develop new models for applause.
Outcome: The proposed model predicts moments of audience applause from speeches at campaign rallies, rallies and rallies.
Attending to Long-Distance Document Context for Sequence Labeling (2020.findings-emnlp)

Copied to clipboard

Challenge: UC Berkeley researchers develop a method for incorporating global context in long documents . many of the main datasets used in NLP are comprised of relatively short documents - english OntoNotes contains 223 tokens .
Approach: They propose a method for incorporating global context in long documents . they use multiple mentions of the same word type to generate a representation for each token .
Outcome: The proposed model performs better at recognizing entities with high TF-IDF scores than parametric models lacking context.

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