: Vocabulaire du TAL: subword units

computational linguistics > linguistic concept > linguistic unit > token > subword units

subword units

In these systems the POS feature is replaced by the embedding i.e. the systems input is the word or subword unit and its corresponding embedding. (Liu, Bao, Gao, Zhang & Wang, 2018)
Speech recognition by directly using optimized subword units has also (Kneissler and Klakow 2001) proven a good approach for speech recognition of a morphologically rich language. (Varjokallio & Klakow, 2016)
Subword units can be computationally discovered by unsupervised segmentation over words that are regarded as character sequences. (Bai & Zhao, 2018)
This family comprises data-driven algorithms that generate statistically significant subwords units. (Gaido, Savoldi, Bentivogli, Negri & Turchi, 2021)
To better understand the role of subword embedding in sentence pair modeling we performed experimental comparisons that vary (1) the type of subword unit (2) the composition function and (3) the datasets of different characteristics. (Lan & Xu, 2018)

http://data.loterre.fr/ark:/67375/8LP-P31Z54H1-8

RDF/XML TURTLE JSON-LD Dernière modification le 27/05/2024

Loterre