Extracting Sentence Embeddings from Pretrained Transformer Models

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in retrieval-augmented generation. But do commonly used plain averaging or pr...

Full description

Bibliographic Details

Main Authors:	Lukas Stankevičius, Mantas Lukoševičius
Format:	Artigo
Language:	Inglês
Published:	MDPI AG 2024-10-01
Series:	Applied Sciences
Subjects:	BERT embeddings large language models natural language processing text embeddings sentence vector representation
Online Access:	https://www.mdpi.com/2076-3417/14/19/8887
Tags:	Add Tag No Tags, Be the first to tag this record!