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

Visa fullständig post



Permalänk

http://hdl.handle.net/10138/311873

Citation

Talman , A , Suni , A , Celikkanat , H , Kakouros , S , Tiedemann , J & Vainio , M 2019 , Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations . in M Hartmann & B Plank (eds) , 22nd Nordic Conference on Computational Linguistics (NoDaLiDa) : Proceedings of the Conference . Linköping Electronic Conference Proceedings , no. 167 , NEALT Proceedings Series , no. 42 , Linköping University Electronic Press , Linköping , pp. 281–290 , Nordic Conference on Computational Linguistics , Turku , Finland , 30/09/2019 .

Titel: Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations
Författare: Talman, Aarne; Suni, Antti; Celikkanat, Hande; Kakouros, Sofoklis; Tiedemann, Jörg; Vainio, Martti
Medarbetare: Hartmann, Mareike
Plank, Barbara
Upphovmannens organisation: Department of Digital Humanities
Language Technology
Phonetics
Phonetics and Speech Synthesis
Mind and Matter
Utgivare: Linköping University Electronic Press
Datum: 2019-09-30
Språk: eng
Sidantal: 10
Tillhör serie: 22nd Nordic Conference on Computational Linguistics (NoDaLiDa)
Tillhör serie: Linköping Electronic Conference Proceedings - NEALT Proceedings Series
ISBN: 978-91-7929-995-8
ISSN: 1650-3686
Permanenta länken (URI): http://hdl.handle.net/10138/311873
Abstrakt: 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 are publicly available.
Subject: 113 Computer and information sciences
Natural language processing
6121 Languages
Referentgranskad: Ja
Licens: cc_by
Användningsbegränsning: openAccess
Parallelpublicerad version: publishedVersion


Filer under denna titel

Totalt antal nerladdningar: Laddar...

Filer Storlek Format Granska
W19_6129.pdf 572.0Kb PDF Granska/Öppna

Detta dokument registreras i samling:

Visa fullständig post