<?xml version="1.0"?>

<!DOCTYPE owl [
	<!ENTITY rdf "http://www.w3.org/1999/02/22-rdf-syntax-ns#">
	<!ENTITY rdfs "http://www.w3.org/2000/01/rdf-schema#">
	<!ENTITY xsd "http://www.w3.org/2001/XMLSchema#">
	<!ENTITY owl "http://www.w3.org/2002/07/owl#">
	<!ENTITY cc "http://web.resource.org/cc/#">
	<!ENTITY project "http://ebiquity.umbc.edu/ontology/project.owl#">
	<!ENTITY person "http://ebiquity.umbc.edu/ontology/person.owl#">
	<!ENTITY pub "http://ebiquity.umbc.edu/ontology/publication.owl#">
	<!ENTITY assert "http://ebiquity.umbc.edu/ontology/assertion.owl#">
]>

<!--

This ontology document is licensed under the Creative Commons
Attribution License. To view a copy of this license, visit
http://creativecommons.org/licenses/by/2.0/ or send a letter to
Creative Commons, 559 Nathan Abbott Way, Stanford, California
94305, USA.

-->

<rdf:RDF 
		xmlns:rdf = "&rdf;"
		xmlns:rdfs = "&rdfs;"
		xmlns:xsd = "&xsd;"
		xmlns:owl = "&owl;"
		xmlns:cc = "&cc;"
		xmlns:project = "&project;"
		xmlns:person = "&person;"
		xmlns:pub = "&pub;"
		xmlns:assert = "&assert;">
	<pub:Proceedings rdf:about="http://ebiquity.umbc.edu/paper/html/id/786/Understanding-the-Logical-and-Semantic-Structure-of-Large-Documents">
		<rdfs:label><![CDATA[Understanding the Logical and Semantic Structure of Large Documents]]></rdfs:label>
		<pub:title><![CDATA[Understanding the Logical and Semantic Structure of Large Documents]]></pub:title>
		<pub:publishedOn rdf:datatype="&xsd;dateTime">2017-04-27T00:00:00-05:00</pub:publishedOn>
		<pub:abstract><![CDATA[Up-to-the-minute language understanding approaches are mostly focused on small documents such as newswire articles, blog posts, product reviews and discussion forum en- tries. Understanding and extracting information from large documents such as legal docu- ments, reports, proposals, technical manuals and research articles is still a challenging task. The reason behind this challenge is that the documents may be multi-themed, complex and cover diverse topics. For example, business opportunities may contain information on the background of the business, product or service of the business, plan, team management, financial or budget related data, competitors, logistics, compliance, legal information and boilerplate content that is repeated across documents. The content can be split into multiple files or aggregated into one large file. As a result, the content in the whole document may have different structures and formats. Furthermore, the information is expressed in differ- ent forms such as paragraphs of text, headers, data forms, tables, images, mathematical equations, lists or a nested combination of these structures.]]></pub:abstract>
		<pub:counter>1178</pub:counter>
		<pub:tag><![CDATA[learning]]></pub:tag>
		<pub:tag><![CDATA[natural language processing]]></pub:tag>
		<pub:booktitle><![CDATA[SDM 2016 Doctoral Forum, SIAM International Conference on Data Mining ]]></pub:booktitle>
		<pub:publisher><![CDATA[SIAM]]></pub:publisher>
		<pub:author>
			<rdf:List>
				<rdf:first>
					<person:Person rdf:about="http://ebiquity.umbc.edu/person/html/Muhammad/Rahman"><person:name><![CDATA[Muhammad Mahbubur Rahman]]></person:name><rdfs:label><![CDATA[Muhammad Mahbubur Rahman]]></rdfs:label></person:Person>
				</rdf:first>
				<rdf:rest rdf:resource="&rdf;nil" />
			</rdf:List>
		</pub:author>
		<pub:firstAuthor>
<person:Person rdf:about="http://ebiquity.umbc.edu/person/html/Muhammad/Rahman"><person:name><![CDATA[Muhammad Mahbubur Rahman]]></person:name><rdfs:label><![CDATA[Muhammad Mahbubur Rahman]]></rdfs:label></person:Person>
		</pub:firstAuthor>
		<pub:softCopy><pub:SoftCopy>
			<pub:softCopyFormat><![CDATA[PDF Document]]></pub:softCopyFormat>
			<pub:softCopyURI><![CDATA[http://ebiquity.umbc.edu/get/a/publication/858.pdf]]></pub:softCopyURI>
			<pub:softCopySize>545003</pub:softCopySize>
			</pub:SoftCopy>
			</pub:softCopy>
	</pub:Proceedings>

<rdf:Description rdf:about="">
	<cc:License rdf:resource="http://creativecommons.org/licenses/by/2.0/" />
</rdf:Description>

</rdf:RDF>
