natural-language-processing-9
Prosody Prediction
3260 papers • 126 benchmarks • 313 datasets
Predicting prosodic prominence from text. This is a 2-way classification task, assigning each word in a sentence a label 1 (prominent) or 0 (non-prominent). ( Image credit: Helsinki Prosody Corpus )
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in prosody-prediction-27
Trend
Dataset
Best Model
Actions
Helsinki Prosody Corpus
Helsinki Prosody Corpus
Libraries
iUse these libraries to find prosody-prediction-27 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
J. Tiedemann, Aarne Talman, Antti Suni, H. Çelikkanat, Sofoklis Kakouros, M. Vainio•Mon Aug 05 2019
A new natural language processing dataset and benchmark for predicting prosodic prominence from written text and shows that pre-trained contextualized word representations from BERT outperform the other models even with less than 10% of the training data.
31