Papers by Jon Gillick
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. |