{"id":"https://openalex.org/W2038248441","doi":"https://doi.org/10.1145/1390334.1390528","title":"On document splitting in passage detection","display_name":"On document splitting in passage detection","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W2038248441","doi":"https://doi.org/10.1145/1390334.1390528","mag":"2038248441"},"language":"en","primary_location":{"id":"doi:10.1145/1390334.1390528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","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/A5036610566","display_name":"Nazli Goharian","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nazli Goharian","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA","[Illinois Institute of Technology, Chicago, IL, USA.]"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"[Illinois Institute of Technology, Chicago, IL, USA.]","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067779098","display_name":"Saket S. R. Mengle","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saket S.R. Mengle","raw_affiliation_strings":["Illinois Institute of Technology, Chicago, IL, USA","[Illinois Institute of Technology, Chicago, IL, USA.]"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology, Chicago, IL, USA","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"[Illinois Institute of Technology, Chicago, IL, USA.]","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036610566"],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":null,"apc_paid":null,"fwci":1.1732,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.84093567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"833","last_page":"834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991000294685364,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9991000294685364,"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":0.9984999895095825,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9916999936103821,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7220719456672668},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6028208136558533},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5866086483001709},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5769822001457214},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5590351819992065},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.520962119102478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4806869924068451},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.46508923172950745},{"id":"https://openalex.org/keywords/document-management-system","display_name":"Document management system","score":0.42539331316947937},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41242384910583496},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3997640609741211},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39293134212493896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7220719456672668},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6028208136558533},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5866086483001709},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5769822001457214},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5590351819992065},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.520962119102478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4806869924068451},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.46508923172950745},{"id":"https://openalex.org/C2278759","wikidata":"https://www.wikidata.org/wiki/Q831677","display_name":"Document management system","level":2,"score":0.42539331316947937},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41242384910583496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3997640609741211},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39293134212493896},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1390334.1390528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390334.1390528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.145.7668","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.145.7668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ir.iit.edu/publications/downloads/goharian838.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2007646767","https://openalex.org/W2018940048","https://openalex.org/W2203835818"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934","https://openalex.org/W2035261173","https://openalex.org/W2106892947","https://openalex.org/W2741401452"],"abstract_inverted_index":{"Passages":[0],"can":[1],"be":[2],"hidden":[3,33],"within":[4,35],"a":[5,36,50,61],"text":[6,51],"to":[7,20,30,55],"circumvent":[8],"their":[9],"disallowed":[10],"transfer.":[11],"Such":[12],"release":[13],"of":[14,18],"compartmentalized":[15],"information":[16],"is":[17,40,53],"concern":[19],"all":[21],"corporate":[22],"and":[23,49,74],"governmental":[24],"organization.":[25],"We":[26,59],"explore":[27],"the":[28],"methodology":[29],"detect":[31],"such":[32,57],"passages":[34,43],"document.":[37],"A":[38],"document":[39,46,63],"divided":[41],"into":[42],"using":[44],"various":[45],"splitting":[47,64],"techniques,":[48],"classifier":[52],"used":[54],"categorize":[56],"passages.":[58],"present":[60],"novel":[62],"technique":[65],"called":[66],"dynamic":[67],"windowing,":[68],"which":[69],"significantly":[70],"improves":[71],"precision,":[72],"recall":[73],"F1":[75],"measure.":[76]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
