Unveiling Key Aspects of Fine-Tuning in Sentence Embeddings: A Representation Rank Analysis

The latest advancements in unsupervised learning of sentence embeddings predominantly involve employing contrastive learning-based (CL-based) fine-tuning over pre-trained language models. In this study, we analyze the latest sentence embedding methods by adopting representation rank as the primary t...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Euna Jung, Jaeill Kim, Jungmin Ko, Jinwoo Park, Wonjong Rhee
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2024-01-01
Serier:	IEEE Access
Fag:	Sentence embedding self-supervised learning contrastive learning fine-tuning representation rank
Online adgang:	https://ieeexplore.ieee.org/document/10734111/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!