Fiche du document
Auteur
Type de document
Périmètre
Langue
Identifiants
- handle: 10670/1.e3oytr
- https://openmethods.dariah.eu/2019/08/12/do-humanists-need-bert-the-stone-and-the-shell/
Organisation
Mots-clés
Computational linguistics Machine Learning science fiction Analysis Sentiment Analysis Digital Humanities Text Categorization machine learning Research Activities Modeling neural networks Text Classification Natural language processing Structural Analysis Tools Google Books sentiment analysis logistic regressionSujets proches
Methods of analysis Analysis and chemistry Analytical methods Chemical analysis Analysis methods Analysis and examinationCiter ce document
Christopher Nunn, « OpenMethods introduction to: Do humanists need BERT? », OpenMethods: Highlighting Digital Humanities Methods and Tools, ID : 10670/1.e3oytr
Métriques
Partage / Export
Résumé
Introduction: Ted Underwood tests a new language representation model called “Bidirectional Encoder Representations from Transformers” (BERT) and asks if humanists should use it. Due to its high degree of difficulty and its limited success (e.g. in questions of genre detection) he concludes, that this approach will be important in the future but it’s nothing to deal with for humanists at the moment. An important caveat worth reading.