{"id":{"repo_id":"unt","oai_identifier":"info:ark/67531/metadc67939"},"canonical_url":"https://search.ndltd.org/etd/unt/info:ark/67531/metadc67939","repository":{"repo_id":"unt","name":"University of North Texas","base_url":"https://digital.library.unt.edu/oai/"},"display":{"title":"Graph-Based Keyphrase Extraction Using Wikipedia","abstract":"Keyphrases describe a document in a coherent and simple way, giving the prospective reader a way to quickly determine whether the document satisfies their information needs. The pervasion of huge amount of information on Web, with only a small amount of documents have keyphrases extracted, there is a definite need to discover automatic keyphrase extraction systems. Typically, a document written by human develops around one or more general concepts or sub-concepts. These concepts or sub-concepts should be structured and semantically related with each other, so that they can form the meaningful representation of a document. Considering the fact, the phrases or concepts in a document are related to each other, a new approach for keyphrase extraction is introduced that exploits the semantic relations in the document. For measuring the semantic relations between concepts or sub-concepts in the document, I present a comprehensive study aimed at using collaboratively constructed semantic resources like Wikipedia and its link structure. In particular, I introduce a graph-based keyphrase extraction system that exploits the semantic relations in the document and features such as term frequency. I evaluated the proposed system using novel measures and the results obtained compare favorably with previously published results on established benchmarks.","abstract_html":"Keyphrases describe a document in a coherent and simple way, giving the prospective reader a way to quickly determine whether the document satisfies their information needs. The pervasion of huge amount of information on Web, with only a small amount of documents have keyphrases extracted, there is a definite need to discover automatic keyphrase extraction systems. Typically, a document written by human develops around one or more general concepts or sub-concepts. These concepts or sub-concepts should be structured and semantically related with each other, so that they can form the meaningful representation of a document. Considering the fact, the phrases or concepts in a document are related to each other, a new approach for keyphrase extraction is introduced that exploits the semantic relations in the document. For measuring the semantic relations between concepts or sub-concepts in the document, I present a comprehensive study aimed at using collaboratively constructed semantic resources like Wikipedia and its link structure. In particular, I introduce a graph-based keyphrase extraction system that exploits the semantic relations in the document and features such as term frequency. I evaluated the proposed system using novel measures and the results obtained compare favorably with previously published results on established benchmarks.","abstract_has_math":false,"creators":["Dandala, Bharath"],"institution":"University of North Texas","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Tarau, Paul","Mihalcea, Rada, 1974-","Ruiz, Miguel E."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2010,"date_issued":"2010-12","date_published":"2010-12","updated_at":"2026-11-19T08:46:55Z","subjects":["keyphrase extraction","wikipedia","automatic extraction","pagerank","semantic relatedness"],"languages":["English"],"rights":["Public","Copyright","Dandala, Bharath","Copyright is held by the author, unless otherwise noted. All rights reserved."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digital.library.unt.edu/ark:/67531/metadc67939/","ark: ark:/67531/metadc67939"],"render_values":[{"text":"https://digital.library.unt.edu/ark:/67531/metadc67939/","href":"https://digital.library.unt.edu/ark:/67531/metadc67939/","code":true},{"text":"ark: ark:/67531/metadc67939","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.12794/metadc67939","outbound_label":"DOI","outbound_source":"dc:identifier","record_url":"https://doi.org/10.12794/metadc67939","record_label":"Repository record","record_kind":"doi","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digital.library.unt.edu/oai/?verb=GetRecord&metadataPrefix=oai_dc&identifier=info%3Aark%2F67531%2Fmetadc67939","prefix":"oai_dc"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Tarau, Paul","Mihalcea, Rada, 1974-","Ruiz, Miguel E."]},{"key":"dc:creator","label":"Author","values":["Dandala, Bharath"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2010-12"]},{"key":"dc:publisher","label":"Institution","values":["University of North Texas"]},{"key":"dc:type","label":"Dc Type","values":["Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["keyphrase extraction","wikipedia","automatic extraction","pagerank","semantic relatedness"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:rights","label":"Dc Rights","values":["Public","Copyright","Dandala, Bharath","Copyright is held by the author, unless otherwise noted. All rights reserved."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["doi: 10.12794/metadc67939","https://digital.library.unt.edu/ark:/67531/metadc67939/","ark: ark:/67531/metadc67939"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Keyphrases describe a document in a coherent and simple way, giving the prospective reader a way to quickly determine whether the document satisfies their information needs. The pervasion of huge amount of information on Web, with only a small amount of documents have keyphrases extracted, there is a definite need to discover automatic keyphrase extraction systems. Typically, a document written by human develops around one or more general concepts or sub-concepts. These concepts or sub-concepts should be structured and semantically related with each other, so that they can form the meaningful representation of a document. Considering the fact, the phrases or concepts in a document are related to each other, a new approach for keyphrase extraction is introduced that exploits the semantic relations in the document. For measuring the semantic relations between concepts or sub-concepts in the document, I present a comprehensive study aimed at using collaboratively constructed semantic resources like Wikipedia and its link structure. In particular, I introduce a graph-based keyphrase extraction system that exploits the semantic relations in the document and features such as term frequency. I evaluated the proposed system using novel measures and the results obtained compare favorably with previously published results on established benchmarks."]},{"key":"dc:format","label":"Dc Format","values":["Text"]},{"key":"dc:title","label":"Title","values":["Graph-Based Keyphrase Extraction Using Wikipedia"]}]}],"canonical_facts":{"dc:contributor":["Tarau, Paul","Mihalcea, Rada, 1974-","Ruiz, Miguel E."],"dc:creator":["Dandala, Bharath"],"dc:date":["2010-12"],"dc:description":["Keyphrases describe a document in a coherent and simple way, giving the prospective reader a way to quickly determine whether the document satisfies their information needs. The pervasion of huge amount of information on Web, with only a small amount of documents have keyphrases extracted, there is a definite need to discover automatic keyphrase extraction systems. Typically, a document written by human develops around one or more general concepts or sub-concepts. These concepts or sub-concepts should be structured and semantically related with each other, so that they can form the meaningful representation of a document. Considering the fact, the phrases or concepts in a document are related to each other, a new approach for keyphrase extraction is introduced that exploits the semantic relations in the document. For measuring the semantic relations between concepts or sub-concepts in the document, I present a comprehensive study aimed at using collaboratively constructed semantic resources like Wikipedia and its link structure. In particular, I introduce a graph-based keyphrase extraction system that exploits the semantic relations in the document and features such as term frequency. I evaluated the proposed system using novel measures and the results obtained compare favorably with previously published results on established benchmarks."],"dc:format":["Text"],"dc:identifier":["doi: 10.12794/metadc67939","https://digital.library.unt.edu/ark:/67531/metadc67939/","ark: ark:/67531/metadc67939"],"dc:language":["English"],"dc:publisher":["University of North Texas"],"dc:rights":["Public","Copyright","Dandala, Bharath","Copyright is held by the author, unless otherwise noted. All rights reserved."],"dc:subject":["keyphrase extraction","wikipedia","automatic extraction","pagerank","semantic relatedness"],"dc:title":["Graph-Based Keyphrase Extraction Using Wikipedia"],"dc:type":["Thesis or Dissertation"]},"updated_at":"2026-11-19T08:46:55Z"}