Fiche du document
1 juin 2018
- handle: 10670/1.knzjer
- hal: hal-01806468
info:eu-repo/semantics/OpenAccess
Sujets proches
Language (New words, slang, etc.) Standard of value Falsehood Credibility Untruthfulness Believability Lying Natural science Sciences Science of science Pseudologia phantastica Lying Measuring Mensuration AssessmentCiter ce document
Bénédicte Pierrejean et al., « Towards Qualitative Word Embeddings Evaluation: Measuring Neighbors Variation », HAL-SHS : linguistique, ID : 10670/1.knzjer
Métriques
Partage / Export
Résumé
We propose a method to study the variation lying between different word embeddings models trained with different parameters. We explore the variation between models trained with only one varying parameter by observing the distributional neighbors variation and show how changing only one parameter can have a massive impact on a given semantic space. We show that the variation is not affecting all words of the semantic space equally. Variation is influenced by parameters such as setting a parameter to its minimum or maximum value but it also depends on the corpus intrinsic features such as the frequency of a word. We identify semantic classes of words remaining stable across the models trained and specific words having high variation.