A novel methodology for retrieving infographics utilizing structure and message content

详细信息    查看全文

• 作者：Zhuo Li^a ; ^{ivanka@udel.edu" class="auth_mail" title="E-mail the corresponding author} ; Sandra Carberry^a ; ^{carberry@udel.edu" class="auth_mail" title="E-mail the corresponding author} ; Hui Fang^b ; ^{hui@udel.edu" class="auth_mail" title="E-mail the corresponding author} ; Kathleen F. McCoy^a ; ^{mccoy@udel.edu" class="auth_mail" title="E-mail the corresponding author} ; Kelly Peterson^a ; ^{keldryc@udel.edu" class="auth_mail" title="E-mail the corresponding author} ; Matthew Stagitis^a ; ^{mattstag@UDel.Edu" class="auth_mail" title="E-mail the corresponding author}
• 关键词：Semi-structured data and XML ; Information retrieval ; Digital libraries ; Query ; Graphic retrieval ; Natural language query processing ; Short document expansion ; Linear combination ranking model
• 刊名：Data & Knowledge Engineering
• 出版年：2015
• 出版时间：November 2015
• 年：2015
• 卷：100
• 期：part_PB
• 页码：191-210
• 全文大小：1518 K

文摘

Information graphics (infographics) in popular media are highly structured knowledge representations that are generally designed to convey an intended message. This paper presents a novel methodology for retrieving infographics from a digital library that takes into account a graphic's structural and message content. The retrieval methodology can be summarized thus: 1) hypothesize requisite structural and message content from a natural language query, 2) measure the relevance of each candidate infographic to the requisite structural and message content hypothesized from the user query, and 3) integrate these relevance measurements via a linear combination model in order to produce a ranked list of infographics in response to the user query. The methodology has been implemented and evaluated, and it significantly outperforms a baseline method that treats queries and graphics as bags of words.