
Unsupervised dimensionality reduction methods like PCA can significantly reduce the dimensionality of sentence embeddings without sacrificing performance in downstream tasks.


coremsg

evaluation-of-unsupervised-dimensionality-reduction-methods-for-pretrained-sentence-embeddings


Evaluation of Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings


title_rewrite


Pretrained Language Models (PLMs) sentence embeddings can be effectively reduced in dimensionality using unsupervised methods like PCA, improving performance in downstream tasks.


pretrained-sentence-embeddings-dimensionality-reduction-evaluation


Pretrained Sentence Embeddings Dimensionality Reduction Evaluation
