Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations

Aarne Talman, Antti Suni, Hande Celikkanat, Sofoklis Kakouros, Jörg Tiedemann, Martti Vainio


Abstract
In this paper we introduce a new natural language processing dataset and benchmark for predicting prosodic prominence from written text. To our knowledge this will be the largest publicly available dataset with prosodic labels. We describe the dataset construction and the resulting benchmark dataset in detail and train a number of different models ranging from feature-based classifiers to neural network systems for the prediction of discretized prosodic prominence. We show that pre-trained contextualized word representations from BERT outperform the other models even with less than 10% of the training data. Finally we discuss the dataset in light of the results and point to future research and plans for further improving both the dataset and methods of predicting prosodic prominence from text. The dataset and the code for the models will be made publicly available.
Anthology ID:
W19-6129
Volume:
Proceedings of the 22nd Nordic Conference on Computational Linguistics
Month:
September–October
Year:
2019
Address:
Turku, Finland
Venues:
NoDaLiDa | WS
SIG:
Publisher:
Linköping University Electronic Press
Note:
Pages:
281–290
Language:
URL:
https://www.aclweb.org/anthology/W19-6129
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W19-6129.pdf