Word sense induction with agglomerative clustering and mutual information maximization

Word sense induction (WSI) is a challenging problem in natural language processing that involves the unsupervised automatic detection of a word’s senses (i.e., meanings). Recent work achieves significant results on the WSI task by pre-training a language model that can exclusively disambiguate word...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Hadi Abdine, Moussa Kamal Eddine, Davide Buscaldi, Michalis Vazirgiannis
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	KeAi Communications Co. Ltd. 2023-01-01
Edice:	AI Open
Témata:	Word sense induction Unsupervised machine learning Natural language processing Transformer BERT Mutual information
On-line přístup:	http://www.sciencedirect.com/science/article/pii/S2666651023000232
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!