{"id":"https://openalex.org/W1978321170","doi":"https://doi.org/10.1145/1089815.1089825","title":"Extracting statistical data frames from text","display_name":"Extracting statistical data frames from text","publication_year":2005,"publication_date":"2005-06-01","ids":{"openalex":"https://openalex.org/W1978321170","doi":"https://doi.org/10.1145/1089815.1089825","mag":"1978321170"},"language":"en","primary_location":{"id":"doi:10.1145/1089815.1089825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1089815.1089825","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","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/A5048980264","display_name":"Jisheng Liang","orcid":"https://orcid.org/0000-0001-8606-9508"},"institutions":[{"id":"https://openalex.org/I4210126054","display_name":"Strategic Insight (United States)","ror":"https://ror.org/0303r7956","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126054"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jisheng Liang","raw_affiliation_strings":["Insightful Corporation, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Insightful Corporation, Seattle, WA","institution_ids":["https://openalex.org/I4210126054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109173865","display_name":"Krzysztof Koperski","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126054","display_name":"Strategic Insight (United States)","ror":"https://ror.org/0303r7956","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126054"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krzysztof Koperski","raw_affiliation_strings":["Insightful Corporation, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Insightful Corporation, Seattle, WA","institution_ids":["https://openalex.org/I4210126054"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026113034","display_name":"Thien Huu Nguyen","orcid":"https://orcid.org/0000-0003-3768-4736"},"institutions":[{"id":"https://openalex.org/I4210126054","display_name":"Strategic Insight (United States)","ror":"https://ror.org/0303r7956","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126054"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thien Nguyen","raw_affiliation_strings":["Insightful Corporation, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Insightful Corporation, Seattle, WA","institution_ids":["https://openalex.org/I4210126054"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049009088","display_name":"Giovanni Marchisio","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126054","display_name":"Strategic Insight (United States)","ror":"https://ror.org/0303r7956","country_code":"US","type":"company","lineage":["https://openalex.org/I4210126054"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Giovanni Marchisio","raw_affiliation_strings":["Insightful Corporation, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Insightful Corporation, Seattle, WA","institution_ids":["https://openalex.org/I4210126054"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048980264"],"corresponding_institution_ids":["https://openalex.org/I4210126054"],"apc_list":null,"apc_paid":null,"fwci":0.9134,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.8038155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"7","issue":"1","first_page":"67","last_page":"75"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9988999962806702,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9983999729156494,"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":0.8809378743171692},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6217706203460693},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.550977349281311},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5004792213439941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45125213265419006},{"id":"https://openalex.org/keywords/unstructured-data","display_name":"Unstructured data","score":0.42107701301574707},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3804158866405487},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3539983034133911},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.20988088846206665},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.14624375104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8809378743171692},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6217706203460693},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.550977349281311},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5004792213439941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45125213265419006},{"id":"https://openalex.org/C2781252014","wikidata":"https://www.wikidata.org/wiki/Q1141900","display_name":"Unstructured data","level":3,"score":0.42107701301574707},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3804158866405487},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3539983034133911},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.20988088846206665},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.14624375104904175},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":2,"locations":[{"id":"doi:10.1145/1089815.1089825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1089815.1089825","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.97.7594","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.97.7594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://kdd.org/explorations/issues/7-1-2005-06/10-Liang.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W108101778","https://openalex.org/W1813235261","https://openalex.org/W1815980765","https://openalex.org/W1877304445","https://openalex.org/W1966944120","https://openalex.org/W1970516776","https://openalex.org/W1971421925","https://openalex.org/W2033319677","https://openalex.org/W2104748762","https://openalex.org/W2121940249","https://openalex.org/W2147152072","https://openalex.org/W2152183901","https://openalex.org/W2169516665","https://openalex.org/W2182079189","https://openalex.org/W4285719527","https://openalex.org/W6604357158"],"related_works":["https://openalex.org/W3203889067","https://openalex.org/W3184725726","https://openalex.org/W2378793138","https://openalex.org/W2759357633","https://openalex.org/W1541499806","https://openalex.org/W2591076968","https://openalex.org/W2761062406","https://openalex.org/W42295635","https://openalex.org/W4241649480","https://openalex.org/W1973996291"],"abstract_inverted_index":{"We":[0,78],"present":[1],"a":[2,20,50,98],"framework":[3,106],"that":[4,26,88],"bridges":[5],"the":[6,39,46],"gap":[7],"between":[8],"natural":[9],"language":[10],"processing":[11],"(NLP)":[12],"and":[13,56,72,85],"text":[14,24,32],"mining.":[15],"Central":[16],"to":[17,23,91],"this":[18,105],"is":[19,63],"new":[21,47],"approach":[22],"parameterization":[25],"captures":[27],"many":[28],"interesting":[29],"attributes":[30],"of":[31,53,69,100,110],"usually":[33],"ignored":[34],"by":[35],"standard":[36],"indices,":[37],"like":[38,95],"term-document":[40],"matrix.":[41],"By":[42],"storing":[43],"NLP":[44],"tags,":[45],"index":[48,62],"supports":[49],"higher":[51],"degree":[52],"knowledge":[54],"discovery":[55],"pattern":[57],"finding":[58],"from":[59],"text.":[60],"The":[61],"relatively":[64],"compact,":[65],"enabling":[66],"dynamic":[67],"search":[68,81],"arbitrary":[70],"relationships":[71],"events":[73],"in":[74,83],"large":[75],"document":[76],"collections.":[77],"can":[79,107],"export":[80],"results":[82],"formats":[84],"data":[86],"structures":[87],"are":[89],"transparent":[90],"statistical":[92,115],"analysis":[93],"tools":[94],"S-PLUSID\u00ae.":[96],"In":[97],"number":[99],"experiments,":[101],"we":[102],"demonstrate":[103],"how":[104],"turn":[108],"mountains":[109],"unstructured":[111],"information":[112],"into":[113],"informative":[114],"graphs.":[116]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}