Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cuscito, Miriam, Ferrara, Alfio, Ruskov, Martin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2402.05034
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929237150138368
author Cuscito, Miriam
Ferrara, Alfio
Ruskov, Martin
author_facet Cuscito, Miriam
Ferrara, Alfio
Ruskov, Martin
contents In this paper, we explore the idea of analysing the historical bias of contextual language models based on BERT by measuring their adequacy with respect to Early Modern (EME) and Modern (ME) English. In our preliminary experiments, we perform fill-in-the-blank tests with 60 masked sentences (20 EME-specific, 20 ME-specific and 20 generic) and three different models (i.e., BERT Base, MacBERTh, English HLM). We then rate the model predictions according to a 5-point bipolar scale between the two language varieties and derive a weighted score to measure the adequacy of each model to EME and ME varieties of English.
format Preprint
id arxiv_https___arxiv_org_abs_2402_05034
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models
Cuscito, Miriam
Ferrara, Alfio
Ruskov, Martin
Computation and Language
Computers and Society
I.2.7; J.5
In this paper, we explore the idea of analysing the historical bias of contextual language models based on BERT by measuring their adequacy with respect to Early Modern (EME) and Modern (ME) English. In our preliminary experiments, we perform fill-in-the-blank tests with 60 masked sentences (20 EME-specific, 20 ME-specific and 20 generic) and three different models (i.e., BERT Base, MacBERTh, English HLM). We then rate the model predictions according to a 5-point bipolar scale between the two language varieties and derive a weighted score to measure the adequacy of each model to EME and ME varieties of English.
title How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models
topic Computation and Language
Computers and Society
I.2.7; J.5
url https://arxiv.org/abs/2402.05034