arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.05034cs.CLcs.CY
收藏

BERT 如何说莎士比亚式英语?评估上下文语言模型中的历史偏见

How BERT Speaks Shakespearean English? Evaluating Historical Bias in Contextual Language Models

Università degli Studi di Cassino e del Lazio Meridionale(卡西诺和南拉齐奥大学);Università degli Studi di Milano(米兰大学)

Miriam Cuscito, Alfio Ferrara, Martin Ruskov

AI总结:

本文通过填空测试和加权评分,评估基于 BERT 的上下文语言模型对早期现代英语与现代英语的历史适配度,揭示其历史偏见。

摘要:

本文探讨了基于 BERT 的上下文语言模型的历史偏见分析思路,通过衡量这些模型对早期现代英语(EME)和现代英语(ME)的适配度来实现。在初步实验中,我们使用 60 个掩码句子(20 个 EME 特定、20 个 ME 特定和 20 个通用)和三种不同模型(即 BERT Base、MacBERTh、English HLM)进行填空测试。随后,我们根据两种语言变体之间的 5 点双极量表对模型预测进行评分,并得出一个加权分数来衡量每个模型对 EME 和 ME 英语变体的适配度。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑