Characterizing the impact of geometric properties of word embeddings on task performance

Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of embedding features in downstream models, and are largely unexplor...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Whitaker, Brendan, Newman-Griffis, Denis, Haldar, Aparajita, Ferhatosmanoglu, Hakan, Fosler-Lussier, Eric
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computation and Language Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!