: Vocabulaire du TAL: similarity measure

NLP resources and evaluation > measure > similarity measure

similarity measure

For a given set of queries Q the attention uses a similarity function to compare each query with a set of keys K. (Helcl, Libovický & Variš, 2018)
For calculating the similarity measures we concatenate the essays of the successful applicants and create a corpus which is used for comparison with both training and testing data. (Kanojia, Wani & Bhattacharyya, 2017)
The similarity measure is computed between vectors encoding not only the words in the window but also the speakers who uttered the words. (Camelin, Damnati, Bouchekif, Landeau, Charlet & Estève, 2018)
To make our model robust to alignment noise we use only content words to compute the similarity function. (Padó & Lapata, 2006)
We performed domain adaptation of language data using a combination of similarity metrics. (Wolk & Marasek, 2017)

http://data.loterre.fr/ark:/67375/8LP-K2DJ0MHQ-6

RDF/XML TURTLE JSON-LD Date de création 26/06/2024, dernière modification le 26/06/2024

Loterre