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...

Бүрэн тодорхойлолт

Номзүйн дэлгэрэнгүй

Үндсэн зохиолчид:	Minji Kim, Whanhee Cho, Soohyeong Kim, Yong Suk Choi
Формат:	Artigo
Хэл сонгох:	Inglês
Хэвлэсэн:	Wiley 2024-08-01
Цуврал:	Advanced Intelligent Systems
Нөхцлүүд:	contrastive learning sentence embedding syntactic transformation
Онлайн хандалт:	https://doi.org/10.1002/aisy.202300717
Шошгууд:	Шошго нэмэх Шошго байхгүй, Энэхүү баримтыг шошголох эхний хүн болох!