{"id":"https://openalex.org/W2113937265","doi":"https://doi.org/10.1109/icdim.2008.4746719","title":"Use of text syntactical structures in detection of document duplicates","display_name":"Use of text syntactical structures in detection of document duplicates","publication_year":2008,"publication_date":"2008-11-01","ids":{"openalex":"https://openalex.org/W2113937265","doi":"https://doi.org/10.1109/icdim.2008.4746719","mag":"2113937265"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2008.4746719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016133569","display_name":"Mohamed Elhadi","orcid":"https://orcid.org/0000-0002-7966-7224"},"institutions":[{"id":"https://openalex.org/I47818738","display_name":"Sultan Qaboos University","ror":"https://ror.org/04wq8zb47","country_code":"OM","type":"education","lineage":["https://openalex.org/I47818738"]}],"countries":["OM"],"is_corresponding":true,"raw_author_name":"Mohamed Elhadi","raw_affiliation_strings":["Department of Computer Science, Sultan Qaboos University, Oman","Department of Computer Science, Sultan Qaboos University, Al-Khod,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Sultan Qaboos University, Oman","institution_ids":["https://openalex.org/I47818738"]},{"raw_affiliation_string":"Department of Computer Science, Sultan Qaboos University, Al-Khod,","institution_ids":["https://openalex.org/I47818738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066917894","display_name":"Amjad Al-Tobi","orcid":null},"institutions":[{"id":"https://openalex.org/I47818738","display_name":"Sultan Qaboos University","ror":"https://ror.org/04wq8zb47","country_code":"OM","type":"education","lineage":["https://openalex.org/I47818738"]}],"countries":["OM"],"is_corresponding":false,"raw_author_name":"Amjad Al-Tobi","raw_affiliation_strings":["Department of Computer Science, Sultan Qaboos University, Oman","Department of Computer Science, Sultan Qaboos University, Al-Khod,"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Sultan Qaboos University, Oman","institution_ids":["https://openalex.org/I47818738"]},{"raw_affiliation_string":"Department of Computer Science, Sultan Qaboos University, Al-Khod,","institution_ids":["https://openalex.org/I47818738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5016133569"],"corresponding_institution_ids":["https://openalex.org/I47818738"],"apc_list":null,"apc_paid":null,"fwci":4.7234,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94698093,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"520","last_page":"525"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9815000295639038,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8276265859603882},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6936435699462891},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.6126206517219543},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.5927835702896118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5902605652809143},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5889766216278076},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5878700613975525},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5846049189567566},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5728464722633362},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5483447313308716},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4917655289173126},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48842301964759827},{"id":"https://openalex.org/keywords/similitude","display_name":"Similitude","score":0.44522589445114136},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.4413226246833801},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42215263843536377},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.40091246366500854},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23187455534934998},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08702468872070312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276265859603882},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6936435699462891},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.6126206517219543},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.5927835702896118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5902605652809143},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5889766216278076},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5878700613975525},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5846049189567566},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5728464722633362},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5483447313308716},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4917655289173126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48842301964759827},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.44522589445114136},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.4413226246833801},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42215263843536377},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.40091246366500854},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23187455534934998},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08702468872070312},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2008.4746719","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2008.4746719","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 Third International Conference on Digital Information Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6399999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W8870360","https://openalex.org/W1501099340","https://openalex.org/W1522263329","https://openalex.org/W1557168499","https://openalex.org/W1566018662","https://openalex.org/W1937758960","https://openalex.org/W2055043387","https://openalex.org/W2060951907","https://openalex.org/W2109227373","https://openalex.org/W2111295912","https://openalex.org/W2132880933","https://openalex.org/W2148044665","https://openalex.org/W2149182189","https://openalex.org/W2152064395","https://openalex.org/W2153390303","https://openalex.org/W2606203103","https://openalex.org/W2991109989","https://openalex.org/W4236236547","https://openalex.org/W4241051276","https://openalex.org/W6631396606","https://openalex.org/W6633190634"],"related_works":["https://openalex.org/W3145288231","https://openalex.org/W2371263218","https://openalex.org/W2092552144","https://openalex.org/W2354196777","https://openalex.org/W2965473297","https://openalex.org/W2108265183","https://openalex.org/W2257399947","https://openalex.org/W2248278495","https://openalex.org/W2386746909","https://openalex.org/W2387316851"],"abstract_inverted_index":{"This":[0,87,120,138],"is":[1,140],"the":[2,14,55,73,81,84,102,131,145,165],"first":[3],"paper":[4],"on":[5,94,109],"a":[6,20,48,60,66,92,95,172],"set":[7],"of":[8,16,33,40,72,76,80,83,90,98,125,130,167,174,178],"experiments":[9],"addressing":[10],"issues":[11],"related":[12],"to":[13,161],"determination":[15],"text":[17,148],"similarity":[18],"using":[19,59,128,168],"combined":[21],"syntactical":[22,35,176],"representation":[23,177],"and":[24,44,78,116,135,142,150,163],"string":[25,68,133],"alignment":[26,152,157],"techniques.":[27],"The":[28],"suggested":[29],"approach":[30],"takes":[31],"advantage":[32],"document":[34,93],"structure":[36],"manifested":[37],"in":[38,114,118,121,153],"Part":[39],"Speech":[41],"(POS)":[42],"tags":[43],"uses":[45],"it":[46],"as":[47,171],"basis":[49],"for":[50],"further":[51],"processing.":[52],"Documents,":[53],"including":[54],"query,":[56],"are":[57,112,159],"pre-processed":[58],"POS":[61],"tagger":[62],"converting":[63],"them":[64],"into":[65],"reduced":[67],"that":[69,100,105,111],"captures":[70,101],"some":[71,79],"writing":[74],"style":[75],"authors":[77],"semantics":[82],"written":[85],"text.":[86],"provides":[88],"means":[89],"representing":[91],"higher":[96],"level":[97],"abstraction":[99],"different":[103],"alterations":[104],"can":[106],"be":[107],"done":[108],"documents":[110,127],"similar":[113],"origin":[115],"possibly":[117],"style.":[119],"turn":[122],"enables":[123],"processing":[124,149],"such":[126],"many":[129],"available":[132],"manipulation":[134],"matching":[136],"algorithms.":[137],"work":[139],"inspired":[141],"driven":[143],"by":[144],"parallel":[146],"between":[147],"sequence":[151],"computational":[154],"biology.":[155],"Sequence":[156],"techniques":[158],"used":[160],"analyze":[162],"establish":[164],"utility":[166],"strings":[169],"produced":[170],"result":[173],"this":[175],"content.":[179]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
