Sentence part-enhanced BERT with respect to downstream tasks

Abstract Bidirectional encoder representations from transformers (BERT) have achieved great success in many natural language processing tasks. However, BERT generally takes the embedding of the first token to represent sentence meaning in the tasks such as sentiment analysis and textual similarity,...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Chaoming Liu, Wenhao Zhu, Xiaoyu Zhang, Qiuhong Zhai
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Springer 2022-07-01
Edice:	Complex & Intelligent Systems
Témata:	Natural language processing BERT Sentence representation Sentence part Fusion strategy
On-line přístup:	https://doi.org/10.1007/s40747-022-00819-1
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!