{"id":"https://openalex.org/W2991392276","doi":"https://doi.org/10.13053/cys-23-3-3263","title":"Identifying Repeated Sections within Documents","display_name":"Identifying Repeated Sections within Documents","publication_year":2019,"publication_date":"2019-10-07","ids":{"openalex":"https://openalex.org/W2991392276","doi":"https://doi.org/10.13053/cys-23-3-3263","mag":"2991392276"},"language":"es","primary_location":{"id":"doi:10.13053/cys-23-3-3263","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-23-3-3263","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-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/A5091609490","display_name":"Girish Keshav Palshikar","orcid":"https://orcid.org/0000-0003-3625-6705"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Girish K. Palshikar","raw_affiliation_strings":["TCS Research & Innovation, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research & Innovation, Pune, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084300718","display_name":"Sachin Pawar","orcid":"https://orcid.org/0000-0002-6531-7127"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sachin Pawar","raw_affiliation_strings":["TCS Research & Innovation, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research & Innovation, Pune, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101908285","display_name":"Rajiv Srivastava","orcid":"https://orcid.org/0000-0002-9466-8647"},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajiv Srivastava","raw_affiliation_strings":["TCS Research & Innovation, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research & Innovation, Pune, India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103968139","display_name":"Mahek Shah","orcid":null},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Mahek Shah","raw_affiliation_strings":["TCS Research & Innovation, Pune, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TCS Research & Innovation, Pune, India","institution_ids":["https://openalex.org/I55215948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.15396455,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"23","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9998000264167786,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9977999925613403,"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":0.7919284105300903},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.703798234462738},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5711656808853149},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5489866137504578},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5172070264816284},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47630393505096436},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.47619354724884033},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4279576539993286},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33355963230133057}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7919284105300903},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.703798234462738},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5711656808853149},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5489866137504578},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5172070264816284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47630393505096436},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.47619354724884033},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4279576539993286},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33355963230133057},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13053/cys-23-3-3263","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-23-3-3263","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2120609574","https://openalex.org/W2147880316","https://openalex.org/W2167492639","https://openalex.org/W2296283641"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2387743295","https://openalex.org/W2115758952","https://openalex.org/W3082787378","https://openalex.org/W2136007095","https://openalex.org/W2366230879","https://openalex.org/W3208425359","https://openalex.org/W2349927912","https://openalex.org/W3159777597","https://openalex.org/W4212839359"],"abstract_inverted_index":{"Identifying":[0],"sections":[1,101,133,157],"containing":[2],"a":[3,8,22,43,117],"logically":[4],"coherent":[5],"text":[6],"about":[7],"particular":[9],"aspect":[10],"is":[11,67,146],"important":[12],"for":[13,58,95],"fine-grained":[14],"IR,":[15],"question-answering":[16],"and":[17,35,50,83,91,124,151],"information":[18],"extraction.":[19],"We":[20,46,111],"propose":[21,150],"novel":[23],"problem":[24,154],"of":[25,42,99,109,119,121,129,141,155],"identifying":[26,60,96,130],"repeated":[27,61,100,132,156],"sections,":[28],"such":[29,131],"as":[30],"project":[31,62],"details":[32],"in":[33,39,106,134],"resumes":[34,49,120],"different":[36,107],"sports":[37],"events":[38],"the":[40,70,113,127,139,147,153],"transcript":[41],"news":[44],"broadcast.":[45],"focus":[47],"on":[48,79,116],"present":[51],"four":[52,114],"techniques":[53,88],"(2":[54],"unsupervised,":[55],"2":[56],"supervised)":[57],"automatically":[59],"sections.":[63],"The":[64,74,86],"knowledge-based":[65],"method":[66],"modeled":[68],"after":[69],"human":[71],"way":[72],"closely.":[73],"other":[75,97],"methods":[76,115],"are":[77,89],"based":[78],"integer":[80],"linear":[81],"programming":[82],"sequence":[84],"labeling.":[85],"proposed":[87],"general":[90],"can":[92],"be":[93],"used":[94],"kinds":[98],"(and":[102],"even":[103],"non-repeating":[104],"sections)":[105],"types":[108],"documents.":[110],"compared":[112],"dataset":[118],"IT":[122],"professionals":[123],"also":[125],"evaluated":[126],"benefits":[128],"practical":[135],"IR":[136],"tasks.":[137],"To":[138],"best":[140],"our":[142],"knowledge,":[143],"this":[144],"paper":[145],"first":[148],"to":[149],"solve":[152],"identification.":[158]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}