Effect of dimensionality change on the bias of word embeddings

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Rai, Rohit Raj, Awekar, Amit
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911743138070528
author Rai, Rohit Raj
Awekar, Amit
author_facet Rai, Rohit Raj
Awekar, Amit
contents Word embedding methods (WEMs) are extensively used for representing text data. The dimensionality of these embeddings varies across various tasks and implementations. The effect of dimensionality change on the accuracy of the downstream task is a well-explored question. However, how the dimensionality change affects the bias of word embeddings needs to be investigated. Using the English Wikipedia corpus, we study this effect for two static (Word2Vec and fastText) and two context-sensitive (ElMo and BERT) WEMs. We have two observations. First, there is a significant variation in the bias of word embeddings with the dimensionality change. Second, there is no uniformity in how the dimensionality change affects the bias of word embeddings. These factors should be considered while selecting the dimensionality of word embeddings.
format Preprint
id arxiv_https___arxiv_org_abs_2312_17292
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Effect of dimensionality change on the bias of word embeddings
Rai, Rohit Raj
Awekar, Amit
Computation and Language
Word embedding methods (WEMs) are extensively used for representing text data. The dimensionality of these embeddings varies across various tasks and implementations. The effect of dimensionality change on the accuracy of the downstream task is a well-explored question. However, how the dimensionality change affects the bias of word embeddings needs to be investigated. Using the English Wikipedia corpus, we study this effect for two static (Word2Vec and fastText) and two context-sensitive (ElMo and BERT) WEMs. We have two observations. First, there is a significant variation in the bias of word embeddings with the dimensionality change. Second, there is no uniformity in how the dimensionality change affects the bias of word embeddings. These factors should be considered while selecting the dimensionality of word embeddings.
title Effect of dimensionality change on the bias of word embeddings
topic Computation and Language
url https://arxiv.org/abs/2312.17292