Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Entire DC Network
Table Extraction Using Conditional Random Fields, David Pinto, Andrew Mccallum, Xing Wei, W. Bruce Croft
Table Extraction Using Conditional Random Fields, David Pinto, Andrew Mccallum, Xing Wei, W. Bruce Croft
Andrew McCallum
The ability to find tables and extract information from them is a necessary component of data mining, question answering, and other information retrieval tasks. Documents often contain tables in order to communicate densely packed, multi-dimensional information. Tables do this by employing layout patterns to efficiently indicate fields and records in two-dimensional form. Their rich combination of formatting and content present difficulties for traditional language modeling techniques, however. This paper presents the use of conditional random fields (CRFs) for table extraction, and compares them with hidden Markov models (HMMs). Unlike HMMs, CRFs support the use of many rich and overlapping layout …
Western States Dublin Core Metadata Best Practices, Version 1.2, Cheryl D. Walters
Western States Dublin Core Metadata Best Practices, Version 1.2, Cheryl D. Walters
Cheryl D. Walters
Funded by a grant awarded by the Institute for Museum and Library Services (IMLS) in the fall of 2001, the University of Denver (Denver, Colorado) spearheaded a multi-state collaborative initiative to create a virtual collection of widely dispersed digital resources on the topic, Western trails. As part of this initiative, 23 institutions in four Western states were awarded mini-grants to create digital content and metadata for resources related to Western trails. In addition to creation of a virtual collection of digital resources, another significant component of this multi-state initiative was development of a set of Dublin-Core based best practices by …