{"id":"https://openalex.org/W1999053255","doi":"https://doi.org/10.1145/1555400.1555412","title":"CEBBIP","display_name":"CEBBIP","publication_year":2009,"publication_date":"2009-06-15","ids":{"openalex":"https://openalex.org/W1999053255","doi":"https://doi.org/10.1145/1555400.1555412","mag":"1999053255"},"language":"en","primary_location":{"id":"doi:10.1145/1555400.1555412","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1555400.1555412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM/IEEE-CS joint conference on Digital libraries","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/A5004474713","display_name":"Liangcai Gao","orcid":"https://orcid.org/0000-0001-9444-1568"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangcai Gao","raw_affiliation_strings":["Institute of Computer Science and Technology of Peking University, Beijing, China","Institute of Computer Science and Technology of Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology of Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Institute of Computer Science and Technology of Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103175239","display_name":"Zhi Tang","orcid":"https://orcid.org/0000-0002-6021-8357"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Tang","raw_affiliation_strings":["Institute of Computer Science and Technology of Peking University, Beijing, China","Institute of Computer Science and Technology of Peking University, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science and Technology of Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Institute of Computer Science and Technology of Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108543316","display_name":"Xiaofan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaofan Lin","raw_affiliation_strings":["Vobile Inc., Santa Clara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vobile Inc., Santa Clara, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"73","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994000196456909,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9944000244140625,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9926000237464905,"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":0.8555448055267334},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.8434135913848877},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6060939431190491},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5826383233070374},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5712182521820068},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5578949451446533},{"id":"https://openalex.org/keywords/citation","display_name":"Citation","score":0.5519282221794128},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.483389288187027},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4598584473133087},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.43993768095970154},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.4324217140674591},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.42500221729278564},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.41550785303115845},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.38129764795303345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36646705865859985},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.179254412651062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8555448055267334},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.8434135913848877},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6060939431190491},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5826383233070374},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5712182521820068},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5578949451446533},{"id":"https://openalex.org/C2778805511","wikidata":"https://www.wikidata.org/wiki/Q1713","display_name":"Citation","level":2,"score":0.5519282221794128},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.483389288187027},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4598584473133087},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.43993768095970154},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.4324217140674591},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.42500221729278564},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.41550785303115845},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.38129764795303345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36646705865859985},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.179254412651062},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1555400.1555412","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1555400.1555412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1519749309","https://openalex.org/W1534730506","https://openalex.org/W1568339100","https://openalex.org/W1992419399","https://openalex.org/W2036401869","https://openalex.org/W2040217811","https://openalex.org/W2097166075","https://openalex.org/W2109757083","https://openalex.org/W2124991807","https://openalex.org/W2140479099","https://openalex.org/W2142362549","https://openalex.org/W2145130412","https://openalex.org/W2163737492"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2093471820","https://openalex.org/W50079190","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W2045514505","https://openalex.org/W1492005981","https://openalex.org/W1982302668","https://openalex.org/W3015234152","https://openalex.org/W2393746579"],"abstract_inverted_index":{"Bibliographic":[0],"information":[1],"is":[2,108,157],"essential":[3],"for":[4,55],"many":[5],"digital":[6],"library":[7],"applications,":[8],"such":[9],"as":[10],"citation":[11,83,91,94,112,132,172],"analysis,":[12],"academic":[13],"searching":[14],"and":[15,49,67,88,135,175],"topic":[16],"discovery.":[17],"And":[18,100],"bibliographic":[19,43],"data":[20,44,63,65,68,72,84,92,116,133,173],"extraction":[21,41],"has":[22,141],"attracted":[23],"a":[24,51,78,86,101,145],"great":[25],"deal":[26],"of":[27,39,42,96,124],"attention":[28],"in":[29,45,85,114,144],"recent":[30],"years.":[31],"In":[32,70],"this":[33],"paper,":[34],"we":[35],"address":[36],"the":[37,56,71,75,115,120,163,171],"problem":[38],"automatic":[40],"Chinese":[46],"electronic":[47],"book":[48,87],"propose":[50],"tool":[52,76,121],"called":[53],"CEBBIP*":[54],"task,":[57],"which":[58],"includes":[59],"three":[60],"main":[61],"systems:":[62],"preprocessing,":[64],"parsing":[66,117,136,176],"postprocessing.":[69],"preprocessing":[73],"system,":[74],"adopts":[77],"rules-based":[79],"method":[80],"to":[81,89,110,130],"locate":[82],"segment":[90],"into":[93],"strings":[95,113],"individual":[97],"referencing":[98],"literature.":[99],"learning-based":[102],"approach,":[103],"Conditional":[104],"Random":[105],"Fields":[106],"(CRF),":[107],"employed":[109],"parse":[111],"system.":[118,149],"Finally,":[119],"takes":[122],"advantage":[123],"document":[125,164],"intrinsic":[126,165],"local":[127,166],"format":[128,167],"consistency":[129,168],"enhance":[131],"segmentation":[134],"through":[137],"clustering":[138],"techniques.":[139],"CEBBIP":[140],"been":[142],"used":[143],"commercial":[146],"E-book":[147],"production":[148],"Experimental":[150],"results":[151],"show":[152],"that":[153],"CEBBIP's":[154],"precision":[155],"rate":[156],"very":[158],"high.":[159],"More":[160],"specially,":[161],"adopting":[162],"obviously":[169],"improves":[170],"segmenting":[174],"accuracy.":[177]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2016-06-24T00:00:00"}