Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Gaifan, Zhou, Yi, Bollegala, Danushka
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914722581839872
author Zhang, Gaifan
Zhou, Yi
Bollegala, Danushka
author_facet Zhang, Gaifan
Zhou, Yi
Bollegala, Danushka
contents Sentence embeddings produced by Pretrained Language Models (PLMs) have received wide attention from the NLP community due to their superior performance when representing texts in numerous downstream applications. However, the high dimensionality of the sentence embeddings produced by PLMs is problematic when representing large numbers of sentences in memory- or compute-constrained devices. As a solution, we evaluate unsupervised dimensionality reduction methods to reduce the dimensionality of sentence embeddings produced by PLMs. Our experimental results show that simple methods such as Principal Component Analysis (PCA) can reduce the dimensionality of sentence embeddings by almost $50\%$, without incurring a significant loss in performance in multiple downstream tasks. Surprisingly, reducing the dimensionality further improves performance over the original high-dimensional versions for the sentence embeddings produced by some PLMs in some tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14001
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings
Zhang, Gaifan
Zhou, Yi
Bollegala, Danushka
Computation and Language
Sentence embeddings produced by Pretrained Language Models (PLMs) have received wide attention from the NLP community due to their superior performance when representing texts in numerous downstream applications. However, the high dimensionality of the sentence embeddings produced by PLMs is problematic when representing large numbers of sentences in memory- or compute-constrained devices. As a solution, we evaluate unsupervised dimensionality reduction methods to reduce the dimensionality of sentence embeddings produced by PLMs. Our experimental results show that simple methods such as Principal Component Analysis (PCA) can reduce the dimensionality of sentence embeddings by almost $50\%$, without incurring a significant loss in performance in multiple downstream tasks. Surprisingly, reducing the dimensionality further improves performance over the original high-dimensional versions for the sentence embeddings produced by some PLMs in some tasks.
title Evaluating Unsupervised Dimensionality Reduction Methods for Pretrained Sentence Embeddings
topic Computation and Language
url https://arxiv.org/abs/2403.14001