{"id":"https://openalex.org/W2124410446","doi":"https://doi.org/10.1145/1014052.1014058","title":"Mining reference tables for automatic text segmentation","display_name":"Mining reference tables for automatic text segmentation","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2124410446","doi":"https://doi.org/10.1145/1014052.1014058","mag":"2124410446"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014058","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5028578280","display_name":"Eugene Agichtein","orcid":"https://orcid.org/0000-0002-3148-5448"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eugene Agichtein","raw_affiliation_strings":["Columbia University"],"affiliations":[{"raw_affiliation_string":"Columbia University","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"last","author":{"id":null,"display_name":"Venkatesh Ganti","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"Venkatesh Ganti","raw_affiliation_strings":["Microsoft Research","Microsoft research#TAB#"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]},{"raw_affiliation_string":"Microsoft research#TAB#","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028578280"],"corresponding_institution_ids":["https://openalex.org/I78577930"],"apc_list":null,"apc_paid":null,"fwci":12.6147,"has_fulltext":false,"cited_by_count":151,"citation_normalized_percentile":{"value":0.98999618,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"20","last_page":"29"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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":0.8494304418563843},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7715595364570618},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7004883885383606},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5581388473510742},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.5009188652038574},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.4751339256763458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44038230180740356},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4260830283164978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8494304418563843},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7715595364570618},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7004883885383606},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5581388473510742},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.5009188652038574},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.4751339256763458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44038230180740356},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4260830283164978},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1014052.1014058","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014058","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.4.7171","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.4.7171","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.columbia.edu/~eugene/papers/kdd04segmentation.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W151003953","https://openalex.org/W1279245896","https://openalex.org/W1516184288","https://openalex.org/W1520232900","https://openalex.org/W1549650444","https://openalex.org/W1560013842","https://openalex.org/W1568339100","https://openalex.org/W1612155886","https://openalex.org/W1921703248","https://openalex.org/W1934019294","https://openalex.org/W1977690962","https://openalex.org/W1982982698","https://openalex.org/W2008652694","https://openalex.org/W2029873015","https://openalex.org/W2048468185","https://openalex.org/W2097927681","https://openalex.org/W2104086170","https://openalex.org/W2105423800","https://openalex.org/W2125838338","https://openalex.org/W2138745909","https://openalex.org/W2140327372","https://openalex.org/W2143349571","https://openalex.org/W2145948275","https://openalex.org/W2153072229","https://openalex.org/W2158823144","https://openalex.org/W2166407869","https://openalex.org/W2169546346","https://openalex.org/W2177750903","https://openalex.org/W2785349534","https://openalex.org/W2950186769","https://openalex.org/W4233527139","https://openalex.org/W4237841550","https://openalex.org/W6606123296","https://openalex.org/W6628082926","https://openalex.org/W6633431331","https://openalex.org/W6644540431"],"related_works":["https://openalex.org/W2592395359","https://openalex.org/W2535231171","https://openalex.org/W2045342254","https://openalex.org/W1501331687","https://openalex.org/W2326647871","https://openalex.org/W4205247302","https://openalex.org/W2468652214","https://openalex.org/W2501551404","https://openalex.org/W1504527458","https://openalex.org/W2130144716"],"abstract_inverted_index":{"Automatically":[0],"segmenting":[1],"unstructured":[2],"text":[3,19,58],"strings":[4],"into":[5,21],"structured":[6],"records":[7],"is":[8,71],"necessary":[9],"for":[10,25],"importing":[11],"the":[12,88,101],"information":[13],"contained":[14],"in":[15,39],"legacy":[16],"sources":[17],"and":[18,30,42,74,76,90],"collections":[20],"a":[22],"data":[23,40],"warehouse":[24],"subsequent":[26],"querying,":[27],"analysis,":[28],"mining":[29],"integration.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,52],"mine":[36],"tables":[37],"present":[38],"warehouses":[41],"relational":[43],"databases":[44],"to":[45],"develop":[46],"an":[47],"automatic":[48],"segmentation":[49,59,69,96],"system.":[50],"Thus,":[51],"overcome":[53],"limitations":[54],"of":[55,92,100],"existing":[56],"supervised":[57,103],"approaches,":[60],"which":[61],"require":[62],"comprehensive":[63],"manually":[64],"labeled":[65],"training":[66],"data.":[67],"Our":[68],"system":[70],"robust,":[72],"accurate,":[73],"efficient,":[75],"requires":[77],"no":[78],"additional":[79],"manual":[80],"effort.":[81],"Thorough":[82],"evaluation":[83],"on":[84],"real":[85],"datasets":[86],"demonstrates":[87],"robustness":[89],"accuracy":[91,97],"our":[93],"system,":[94],"with":[95],"exceeding":[98],"state":[99],"art":[102],"approaches.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":9}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}