@inproceedings{talman-etal-2019-predicting,
title = "Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations",
author = {Talman, Aarne and
Suni, Antti and
Celikkanat, Hande and
Kakouros, Sofoklis and
Tiedemann, J{\"o}rg and
Vainio, Martti},
editor = "Hartmann, Mareike and
Plank, Barbara",
booktitle = "Proceedings of the 22nd Nordic Conference on Computational Linguistics",
month = sep # "–" # oct,
year = "2019",
address = "Turku, Finland",
publisher = {Link{\"o}ping University Electronic Press},
url = "https://aclanthology.org/W19-6129/",
pages = "281--290",
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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="talman-etal-2019-predicting">
<titleInfo>
<title>Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aarne</namePart>
<namePart type="family">Talman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antti</namePart>
<namePart type="family">Suni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hande</namePart>
<namePart type="family">Celikkanat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sofoklis</namePart>
<namePart type="family">Kakouros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martti</namePart>
<namePart type="family">Vainio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-sep–oct</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Nordic Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mareike</namePart>
<namePart type="family">Hartmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Plank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Linköping University Electronic Press</publisher>
<place>
<placeTerm type="text">Turku, Finland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">talman-etal-2019-predicting</identifier>
<location>
<url>https://aclanthology.org/W19-6129/</url>
</location>
<part>
<date>2019-sep–oct</date>
<extent unit="page">
<start>281</start>
<end>290</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
%A Talman, Aarne
%A Suni, Antti
%A Celikkanat, Hande
%A Kakouros, Sofoklis
%A Tiedemann, Jörg
%A Vainio, Martti
%Y Hartmann, Mareike
%Y Plank, Barbara
%S Proceedings of the 22nd Nordic Conference on Computational Linguistics
%D 2019
%8 sep–oct
%I Linköping University Electronic Press
%C Turku, Finland
%F talman-etal-2019-predicting
%X 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.
%U https://aclanthology.org/W19-6129/
%P 281-290
Markdown (Informal)
[Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations](https://aclanthology.org/W19-6129/) (Talman et al., NoDaLiDa 2019)
- Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations (Talman et al., NoDaLiDa 2019)
ACL
- Aarne Talman, Antti Suni, Hande Celikkanat, Sofoklis Kakouros, Jörg Tiedemann, and Martti Vainio. 2019. Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations. In Proceedings of the 22nd Nordic Conference on Computational Linguistics, pages 281–290, Turku, Finland. Linköping University Electronic Press.