{"id":"https://openalex.org/W1601057643","doi":"https://doi.org/10.1109/itre.2004.1393667","title":"Rhetorical structure theory for content-based indexing and retrieval of Web documents","display_name":"Rhetorical structure theory for content-based indexing and retrieval of Web documents","publication_year":2005,"publication_date":"2005-04-06","ids":{"openalex":"https://openalex.org/W1601057643","doi":"https://doi.org/10.1109/itre.2004.1393667","mag":"1601057643"},"language":"en","primary_location":{"id":"doi:10.1109/itre.2004.1393667","doi":"https://doi.org/10.1109/itre.2004.1393667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itre.2004.1393667","pdf_url":null,"source":{"id":"https://openalex.org/S4306419575","display_name":"International Conference on Information Technology: Research and Education","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ITRE 2004. 2nd International Conference Information Technology: Research and Education","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5113492167","display_name":"Farhi Marir","orcid":"https://orcid.org/0000-0002-8014-5693","observed_orcids":["https://orcid.org/0000-0002-8014-5693"]},"institutions":[{"id":"https://openalex.org/I126193024","display_name":"London Metropolitan University","ror":"https://ror.org/00ae33288","country_code":"GB","type":"education","lineage":["https://openalex.org/I126193024"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"F. Marir","raw_affiliation_strings":["School of Informatics & Multimedia Technology, University of North London, UK","Sch. of Informatics & Multimedia Technol., North London Univ., UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics & Multimedia Technology, University of North London, UK","institution_ids":["https://openalex.org/I126193024"]},{"raw_affiliation_string":"Sch. of Informatics & Multimedia Technol., North London Univ., UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109061633","display_name":"Kamel Dine Haouam","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126193024","display_name":"London Metropolitan University","ror":"https://ror.org/00ae33288","country_code":"GB","type":"education","lineage":["https://openalex.org/I126193024"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"K. Haouam","raw_affiliation_strings":["School of Informatics & Multimedia Technology, University of North London, UK","Sch. of Informatics & Multimedia Technol., North London Univ., UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Informatics & Multimedia Technology, University of North London, UK","institution_ids":["https://openalex.org/I126193024"]},{"raw_affiliation_string":"Sch. of Informatics & Multimedia Technol., North London Univ., UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126193024"],"apc_list":null,"apc_paid":null,"fwci":0.2407,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.478076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":"msr tr 98 15","issue":null,"first_page":"160","last_page":"164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9740999937057495,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.011500000022351742,"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":0.007799999788403511,"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/rhetorical-structure-theory","display_name":"Rhetorical Structure Theory","score":0.9819999933242798},{"id":"https://openalex.org/keywords/content-based-indexing","display_name":"content-based indexing","score":0.9440000057220459},{"id":"https://openalex.org/keywords/web-document-retrieval","display_name":"web document retrieval","score":0.8069999814033508},{"id":"https://openalex.org/keywords/discourse-relations","display_name":"discourse relations","score":0.8830000162124634},{"id":"https://openalex.org/keywords/cue-phrases","display_name":"cue phrases","score":0.9779999852180481},{"id":"https://openalex.org/keywords/semantic-indexing","display_name":"semantic indexing","score":0.6480000019073486},{"id":"https://openalex.org/keywords/thematic-relationships","display_name":"thematic relationships","score":0.49000000953674316}],"concepts":[{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8386380672454834},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8338561654090881},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7914367318153381},{"id":"https://openalex.org/C192562157","wikidata":"https://www.wikidata.org/wiki/Q316694","display_name":"Rhetorical question","level":2,"score":0.5728373527526855},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5618666410446167},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5606957077980042},{"id":"https://openalex.org/C90288658","wikidata":"https://www.wikidata.org/wiki/Q3318149","display_name":"Human\u2013computer information retrieval","level":3,"score":0.47272390127182007},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.46686363220214844},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4414665400981903},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.42645710706710815},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4229018986225128},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13533470034599304},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/itre.2004.1393667","doi":"https://doi.org/10.1109/itre.2004.1393667","is_oa":false,"landing_page_url":"https://doi.org/10.1109/itre.2004.1393667","pdf_url":null,"source":{"id":"https://openalex.org/S4306419575","display_name":"International Conference on Information Technology: Research and Education","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ITRE 2004. 2nd International Conference Information Technology: Research and Education","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W86161029","https://openalex.org/W1485329667","https://openalex.org/W1535954793","https://openalex.org/W1553682320","https://openalex.org/W1597655096","https://openalex.org/W1974515720","https://openalex.org/W2043837137","https://openalex.org/W2045738181","https://openalex.org/W2136833348","https://openalex.org/W2136987143","https://openalex.org/W2142509047","https://openalex.org/W2165261022","https://openalex.org/W2212340752","https://openalex.org/W2241351546","https://openalex.org/W2939083804","https://openalex.org/W3022707821","https://openalex.org/W3142110574"],"related_works":["https://openalex.org/W1530552299","https://openalex.org/W1551993109","https://openalex.org/W7043221067","https://openalex.org/W1520367701","https://openalex.org/W2081798983","https://openalex.org/W2156653021","https://openalex.org/W1581484355","https://openalex.org/W7095688228","https://openalex.org/W2293341558","https://openalex.org/W187584193"],"abstract_inverted_index":{"The":[0,59,135],"amount":[1],"of":[2,18,38,46,53,66,72,82,101,154],"information":[3,28,128],"available":[4],"on":[5,30,94,150],"the":[6,16,31,36,57,64,70,73,99],"Internet":[7],"is":[8,21,144],"currently":[9],"growing":[10],"at":[11,62],"an":[12],"incredible":[13],"rate.":[14],"However,":[15],"lack":[17],"efficient":[19],"indexing":[20,43,136],"still":[22],"a":[23,39,50,77,85,114,151],"major":[24],"barrier":[25],"to":[26,97],"effective":[27],"retrieval":[29,45,67,129,138],"Web.":[32],"This":[33],"paper":[34,143],"presents":[35],"design":[37],"technique":[40,60,139],"for":[41],"content-based":[42],"and":[44,137,147],"relevant":[47],"documents":[48,54,155],"from":[49],"large":[51],"collection":[52,121],"such":[55],"as":[56,126],"Internet.":[58],"aims":[61],"improving":[63],"quality":[65],"by":[68],"capturing":[69],"semantics":[71],"documents.":[74],"It":[75],"introduces":[76],"thematic":[78],"relationship":[79],"between":[80],"parts":[81],"text":[83],"using":[84,122],"linguistics":[86],"theory":[87,91],"called":[88],"rhetorical":[89,102,133],"structure":[90],"(RST)":[92],"based":[93],"cue":[95],"phrases":[96],"determine":[98],"set":[100],"relations.":[103,134],"Once":[104],"these":[105],"structures":[106],"are":[107],"determined,":[108],"they":[109],"can":[110,117],"be":[111],"saved":[112],"into":[113],"database.":[115],"We":[116],"then":[118],"query":[119],"that":[120],"not":[123],"only":[124],"keywords,":[125],"traditional":[127],"systems,":[130],"but":[131],"also":[132],"described":[140],"in":[141],"this":[142],"under":[145],"development":[146],"initial":[148],"results":[149],"small":[152],"number":[153],"have":[156],"been":[157],"very":[158],"successful.":[159]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2016-06-24T00:00:00"}
