{"id":"https://openalex.org/W2028569501","doi":"https://doi.org/10.1145/1410140.1410180","title":"Automatic keyphrase extraction from scientific documents using N-gram filtration technique","display_name":"Automatic keyphrase extraction from scientific documents using N-gram filtration technique","publication_year":2008,"publication_date":"2008-09-16","ids":{"openalex":"https://openalex.org/W2028569501","doi":"https://doi.org/10.1145/1410140.1410180","mag":"2028569501"},"language":"en","primary_location":{"id":"doi:10.1145/1410140.1410180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1410140.1410180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM symposium on Document engineering","raw_type":"proceedings-article"},"type":"conference-paper","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/A5074527005","display_name":"Niraj Kumar","orcid":"https://orcid.org/0000-0003-3037-1083"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Niraj Kumar","raw_affiliation_strings":["IIIT-Hyderabad, Hyderabad, India","IIIT - Hyderabad, Hyderabad, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT - Hyderabad, Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070586393","display_name":"Kannan Srinathan","orcid":"https://orcid.org/0009-0002-4306-6707"},"institutions":[{"id":"https://openalex.org/I65181880","display_name":"Indian Institute of Technology Hyderabad","ror":"https://ror.org/01j4v3x97","country_code":"IN","type":"education","lineage":["https://openalex.org/I65181880"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Kannan Srinathan","raw_affiliation_strings":["IIIT-Hyderabad, Hyderabad, India","IIIT - Hyderabad, Hyderabad, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT-Hyderabad, Hyderabad, India","institution_ids":["https://openalex.org/I65181880"]},{"raw_affiliation_string":"IIIT - Hyderabad, Hyderabad, India#TAB#","institution_ids":["https://openalex.org/I65181880"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I65181880"],"apc_list":null,"apc_paid":null,"fwci":5.7914,"has_fulltext":false,"cited_by_count":71,"citation_normalized_percentile":{"value":0.97023878,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis 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/T13083","display_name":"Advanced Text Analysis 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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7478865385055542},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.6602654457092285},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6523510217666626},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6496511101722717},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.6240266561508179},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5459044575691223},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5408715009689331},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5389645099639893},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5341274738311768},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4996981620788574},{"id":"https://openalex.org/keywords/filtration","display_name":"Filtration (mathematics)","score":0.46649906039237976},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44579648971557617},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"Keyword extraction","score":0.43712905049324036},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.43387651443481445},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.42739346623420715},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3117418885231018},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16659116744995117},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09485137462615967}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7478865385055542},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.6602654457092285},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6523510217666626},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6496511101722717},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6240266561508179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5459044575691223},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5408715009689331},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5389645099639893},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5341274738311768},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4996981620788574},{"id":"https://openalex.org/C128489963","wikidata":"https://www.wikidata.org/wiki/Q1187724","display_name":"Filtration (mathematics)","level":2,"score":0.46649906039237976},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44579648971557617},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.43712905049324036},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.43387651443481445},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.42739346623420715},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3117418885231018},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16659116744995117},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09485137462615967},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1410140.1410180","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1410140.1410180","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the eighth ACM symposium on Document engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7300000190734863,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W41834883","https://openalex.org/W142417105","https://openalex.org/W1588594383","https://openalex.org/W2060772621","https://openalex.org/W2091895997","https://openalex.org/W2115225696","https://openalex.org/W2116266212","https://openalex.org/W2123005130","https://openalex.org/W2123107811","https://openalex.org/W2143105380","https://openalex.org/W2145766604","https://openalex.org/W2169602691","https://openalex.org/W2234028104","https://openalex.org/W2541482006","https://openalex.org/W4248426528","https://openalex.org/W4248440216"],"related_works":["https://openalex.org/W1997256148","https://openalex.org/W3186733304","https://openalex.org/W2343335642","https://openalex.org/W2795900462","https://openalex.org/W2069275471","https://openalex.org/W2250909759","https://openalex.org/W2357929520","https://openalex.org/W2251767200","https://openalex.org/W2532616038","https://openalex.org/W2787311093"],"abstract_inverted_index":{"In":[0,69],"this":[1],"paper":[2],"we":[3,43,73],"present":[4],"an":[5],"automatic":[6],"Keyphrase":[7],"extraction":[8],"technique":[9],"for":[10,95],"English":[11,124],"documents":[12,96],"of":[13,35,78,80,91,97,123],"scientific":[14,98],"domain.":[15],"The":[16,108],"devised":[17,130,149],"algorithm":[18,62],"uses":[19],"n-gram":[20,40],"filtration":[21,41],"technique,":[22,42,51],"which":[23],"filters":[24],"sophisticated":[25],"n-grams":[26],"{1dnd4}":[27],"along":[28],"with":[29,141,153],"their":[30],"weight":[31],"from":[32],"the":[33,76,129,148],"words":[34],"input":[36],"document.":[37],"To":[38],"develop":[39],"have":[44,74],"used":[45],"(1)":[46],"LZ78":[47],"data":[48],"compression":[49],"based":[50,112],"(2)":[52],"a":[53,65,135],"simple":[54,59,116],"refinement":[55],"step,":[56],"(3)":[57],"A":[58],"Pattern":[60],"Filtration":[61],"and,":[63],"(4)":[64],"term":[66,70],"weighting":[67,71],"scheme.":[68],"scheme,":[72],"introduced":[75],"importance":[77],"position":[79,90],"sentence":[81,94],"(where":[82],"given":[83],"phrase":[84,92],"occurs":[85],"first)":[86],"in":[87,93],"document":[88],"and":[89,120],"domain":[99],"(which":[100],"is":[101,111,151],"literally":[102],"more":[103],"organized":[104],"than":[105],"other":[106,154],"domains).":[107],"entire":[109],"system":[110,131,150],"upon":[113],"statistical":[114],"observations,":[115],"grammatical":[117],"facts,":[118],"heuristics,":[119],"lexical":[121],"information":[122],"language.":[125],"We":[126],"remark":[127],"that":[128,147],"does":[132],"not":[133],"require":[134],"learning":[136],"phase.":[137],"Our":[138],"experimental":[139],"results":[140],"publically":[142],"available":[143],"text":[144],"dataset,":[145],"shows":[146],"comparable":[152],"known":[155],"algorithms.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}