{"id":"https://openalex.org/W2094673287","doi":"https://doi.org/10.1145/1571941.1572083","title":"Identifying the original contribution of a document via language modeling","display_name":"Identifying the original contribution of a document via language modeling","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2094673287","doi":"https://doi.org/10.1145/1571941.1572083","mag":"2094673287"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1572083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5061572658","display_name":"Benyah Shaparenko","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Benyah Shaparenko","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014687727","display_name":"Thorsten Joachims","orcid":"https://orcid.org/0000-0003-3654-3683"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thorsten Joachims","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061572658"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":0.9033,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.80842639,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"696","last_page":"697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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/T10028","display_name":"Topic Modeling","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9987000226974487,"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":0.8448036909103394},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.8183401823043823},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.677428126335144},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6239348649978638},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.621535062789917},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5731934309005737},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5508409738540649},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5442621111869812},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5080957412719727},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4751051366329193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8448036909103394},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.8183401823043823},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.677428126335144},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6239348649978638},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.621535062789917},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5731934309005737},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5508409738540649},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5442621111869812},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5080957412719727},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4751051366329193},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1571941.1572083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.6531","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.6531","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/People/tj/publications/shaparenko_joachims_09b.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.9823","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.9823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cornell.edu/People/tj/publications/shaparenko_joachims_09a.pdf","raw_type":"text"}],"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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W125892352","https://openalex.org/W318121378","https://openalex.org/W1481997832","https://openalex.org/W1547561528","https://openalex.org/W1574901103","https://openalex.org/W1612003148","https://openalex.org/W1880262756","https://openalex.org/W1978394996","https://openalex.org/W1997763371","https://openalex.org/W2008425387","https://openalex.org/W2027445772","https://openalex.org/W2064153289","https://openalex.org/W2064988570","https://openalex.org/W2072644219","https://openalex.org/W2077122984","https://openalex.org/W2097433297","https://openalex.org/W2106490775","https://openalex.org/W2109154616","https://openalex.org/W2112050062","https://openalex.org/W2112971401","https://openalex.org/W2129294185","https://openalex.org/W2132827946","https://openalex.org/W2135909747","https://openalex.org/W2152706498","https://openalex.org/W2171343266","https://openalex.org/W4231510805","https://openalex.org/W6628747921","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2106813246","https://openalex.org/W2435130738","https://openalex.org/W3107474891","https://openalex.org/W142374489","https://openalex.org/W2359001871","https://openalex.org/W2148757832","https://openalex.org/W1803932089","https://openalex.org/W2351428524","https://openalex.org/W2170640846","https://openalex.org/W1538473846"],"abstract_inverted_index":{"Abstract.":[0],"One":[1],"major":[2],"goal":[3],"of":[4,61,71,114],"text":[5,21],"mining":[6],"is":[7,78,93],"to":[8,12,41,80,97],"provide":[9],"automatic":[10],"methods":[11],"help":[13],"humans":[14],"grasp":[15],"the":[16,34,76,90,101,112,121],"key":[17],"ideas":[18,36],"in":[19,111],"ever-increasing":[20],"corpora.":[22],"To":[23],"this":[24],"effect,":[25],"we":[26],"propose":[27],"a":[28,38,42,69,126],"statistically":[29],"well-founded":[30],"method":[31],"for":[32],"identifying":[33],"original":[35,66,85],"that":[37,120],"document":[39],"contributes":[40],"corpus,":[43],"focusing":[44],"on":[45,104,108],"self-referential":[46],"diachronic":[47],"corpora":[48],"such":[49],"as":[50],"research":[51,115],"publications,":[52],"blogs,":[53],"email,":[54],"and":[55,73,75,95,107,117],"news":[56],"articles.":[57],"Our":[58],"statistical":[59,91],"model":[60,77,92,124],"passage":[62,122],"impact":[63,72,123],"defines":[64],"(interesting)":[65],"content":[67],"through":[68],"combination":[70],"novelty,":[74],"used":[79],"identify":[81],"each":[82],"document\u2019s":[83],"most":[84],"passages.":[86],"Unlike":[87],"heuristic":[88,127],"approaches,":[89],"extensible":[94],"open":[96],"analysis.":[98],"We":[99],"evaluate":[100],"approach":[102],"both":[103],"synthetic":[105],"data":[106,110],"real":[109],"domains":[113],"publications":[116],"news,":[118],"showing":[119],"outperforms":[125],"baseline":[128],"method.":[129],"1":[130]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}