Passer au contenu principal

Vocabulary of natural language processing

Choisissez le vocabulaire dans lequel chercher

Concept information

Terme préférentiel

sequence tagging  

Définition

  • A task which aims to predict from a sequence of words a linguistic tag for each word. (Based on Yang et al., Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks, 2017)

Concept générique

Concepts spécifiques

Synonyme(s)

  • sequence labeling

Contexte(s) définitoire(s)

  • Sequence labeling is an NLP approach that predicts a label for each token within a sequence rather than a label for the whole sequence. (Gandhi, Serrao, Fang, Antonius, Hong, Nguyen, Yi, Nosakhare, Shaffer & Srinivasan, 2022)

Exemple

  • In our work to build the sentence segmentation model we use sequence labeling with the Sentence-BI labeling scheme as discussed in Section 3.2.1. (Gandhi, Serrao, Fang, Antonius, Hong, Nguyen, Yi, Nosakhare, Shaffer & Srinivasan, 2022)
  • Sequence tagging approaches label words as fluent or disfluent using a variety of different techniques including conditional random fields (CRF) (Wang, Wang, Che & Liu, 2020)

Traductions

URI

http://data.loterre.fr/ark:/67375/8LP-CRGC856W-P

Télécharger ce concept :

RDF/XML TURTLE JSON-LD Dernière modification le 15/05/2024