Detecting Family Resemblance: Automated Genre Classification

Data Science Journal

Yunhyong Kim¹  Seamus Ross¹ 

[1] Digital Curation Centre (DCC) & Humanities Advanced Technology Information Institute (HATII), University of Glasgow

关键词: Automated genre classification;    Metadata;    Scientific information;    Information management;    Information extraction;   

DOI  :  10.2481/dsj.6.S172

学科分类：计算机科学（综合）

来源: Ubiquity Press Ltd.

【 摘 要 】

References(40)This paper presents results in automated genre classification of digital documents in PDF format. It describes genre classification as an important ingredient in contextualising scientific data and in retrieving targetted material for improving research. The current paper compares the role ofvisual layout, stylistic features, and language model features in clustering documents and presents results in retrieving five selected genres (Scientific Article, Thesis, Periodicals, Business Report, and Form) from a pool of materials populated with documents of the nineteen most popular genres found in our experimental data set.

【 授权许可】

Unknown