Simple Data Transformations for Mitigating the Syntactic Similarity to Improve Sentence Embeddings at Supervised Contrastive Learning

Contrastive learning of sentence representations has achieved great improvements in several natural language processing tasks. However, the supervised contrastive learning model trained on the natural language inference (NLI) dataset is insufficient to elucidate the semantics of sentences since it i...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Minji Kim, Whanhee Cho, Soohyeong Kim, Yong Suk Choi
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Wiley 2024-08-01
Schriftenreihe:	Advanced Intelligent Systems
Schlagworte:	contrastive learning sentence embedding syntactic transformation
Online-Zugang:	https://doi.org/10.1002/aisy.202300717
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!