An Analysis of BERT (NLP) for Assisted Subject Indexing for Project Gutenberg

IF 0.9 Q3 INFORMATION SCIENCE & LIBRARY SCIENCE

Cataloging & Classification Quarterly Pub Date : 2022-11-17 DOI:10.1080/01639374.2022.2138666

Charlene Chou, Tony Chu

引用次数: 1

Abstract

Abstract In light of AI (Artificial Intelligence) and NLP (Natural language processing) technologies, this article examines the feasibility of using AI/NLP models to enhance the subject indexing of digital resources. While BERT (Bidirectional Encoder Representations from Transformers) models are widely used in scholarly communities, the authors assess whether BERT models can be used in machine-assisted indexing in the Project Gutenberg collection, through suggesting Library of Congress subject headings filtered by certain Library of Congress Classification subclass labels. The findings of this study are informative for further research on BERT models to assist with automatic subject indexing for digital library collections.

查看原文本刊更多论文

BERT（NLP）在古腾堡项目辅助主题标引中的应用分析

摘要本文结合人工智能（AI）和自然语言处理（NLP）技术，探讨了利用AI/NLP模型增强数字资源主题标引的可行性。虽然BERT（来自变压器的双向编码器表示）模型在学术界被广泛使用，但作者通过建议国会图书馆的主题标题被某些国会图书馆分类子类标签过滤，来评估BERT模型是否可以用于古腾堡项目收藏中的机器辅助索引。这项研究的结果为进一步研究BERT模型提供了信息，以帮助数字图书馆馆藏的自动主题索引。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Cataloging & Classification Quarterly INFORMATION SCIENCE & LIBRARY SCIENCE-

CiteScore

0.90

自引率

28.60%

发文量

期刊介绍： Cataloging & Classification Quarterly provides an effective international forum for information and discussion in the field of bibliographic organization. This highly respected journal considers the full spectrum of creation, content, management, use, and usability of bibliographic records, including the principles, functions, and techniques of descriptive cataloging; the wide range of methods of subject analysis and classification; provision of access for all formats of materials; and policies, planning, and issues connected to the effective use of bibliographic data in modern society.