{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/predicting-prosodic-prominence-from-text-with","title":"Predicting Prosodic Prominence from Text with Pre-trained Contextualized Word Representations","arxiv_id":"1908.02262","date":"2019-08-06","proceeding":"WS (NoDaLiDa) 2019 9","authors":["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 are publicly available.","url_abs":"https://arxiv.org/abs/1908.02262v1","url_pdf":"https://arxiv.org/pdf/1908.02262v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"predicting-prosodic-prominence-from-text-with","repo_url":"https://github.com/Helsinki-NLP/prosody","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"prosody-prediction","task_name":"Prosody Prediction"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[{"slug":"helsinki-prosody-corpus","name":"Helsinki Prosody Corpus","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/prosody-prediction-on-helsinki-prosody-corpus","task":"Prosody Prediction","dataset":"Helsinki Prosody Corpus","model":"BERT","rank_in_archive_order":1,"of":4,"metrics":{"Accuracy":"83.2"},"uses_additional_data":false},{"leaderboard":"/sota/prosody-prediction-on-helsinki-prosody-corpus","task":"Prosody Prediction","dataset":"Helsinki Prosody Corpus","model":"BiLSTM","rank_in_archive_order":2,"of":4,"metrics":{"Accuracy":"82.1"},"uses_additional_data":false},{"leaderboard":"/sota/prosody-prediction-on-helsinki-prosody-corpus","task":"Prosody Prediction","dataset":"Helsinki Prosody Corpus","model":"CRF (MarMoT)","rank_in_archive_order":3,"of":4,"metrics":{"Accuracy":"81.8"},"uses_additional_data":false},{"leaderboard":"/sota/prosody-prediction-on-helsinki-prosody-corpus","task":"Prosody Prediction","dataset":"Helsinki Prosody Corpus","model":"SVN (Minitagger)","rank_in_archive_order":4,"of":4,"metrics":{"Accuracy":"80.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.02262","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}