{"id":"https://openalex.org/W2946584807","doi":"https://doi.org/10.1145/3319921.3319970","title":"Employing Auto-Annotated Data for Government Document Classification","display_name":"Employing Auto-Annotated Data for Government Document Classification","publication_year":2019,"publication_date":"2019-03-15","ids":{"openalex":"https://openalex.org/W2946584807","doi":"https://doi.org/10.1145/3319921.3319970","mag":"2946584807"},"language":"en","primary_location":{"id":"doi:10.1145/3319921.3319970","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319921.3319970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence","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/A5075261068","display_name":"Yajun Song","orcid":"https://orcid.org/0000-0002-1543-4691"},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yajun Song","raw_affiliation_strings":["CETC Big Data Research Institute Co., Ltd., Guiyang, China"],"affiliations":[{"raw_affiliation_string":"CETC Big Data Research Institute Co., Ltd., Guiyang, China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084587716","display_name":"Zeyuan Li","orcid":"https://orcid.org/0009-0006-2088-8707"},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeyuan Li","raw_affiliation_strings":["CETC Big Data Research Institute Co., Ltd., Guiyang, China"],"affiliations":[{"raw_affiliation_string":"CETC Big Data Research Institute Co., Ltd., Guiyang, China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049875848","display_name":"Jie He","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie He","raw_affiliation_strings":["CETC Big Data Research Institute Co., Ltd., Guiyang, China"],"affiliations":[{"raw_affiliation_string":"CETC Big Data Research Institute Co., Ltd., Guiyang, China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044786927","display_name":"Zesong Li","orcid":"https://orcid.org/0000-0003-0975-4434"},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zesong Li","raw_affiliation_strings":["CETC Big Data Research Institute Co., Ltd., Guiyang, China"],"affiliations":[{"raw_affiliation_string":"CETC Big Data Research Institute Co., Ltd., Guiyang, China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046642410","display_name":"Xin Fang","orcid":"https://orcid.org/0000-0002-7274-8195"},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Fang","raw_affiliation_strings":["CETC Big Data Research Institute Co., Ltd., Guiyang, China"],"affiliations":[{"raw_affiliation_string":"CETC Big Data Research Institute Co., Ltd., Guiyang, China","institution_ids":["https://openalex.org/I4210096250"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009434777","display_name":"Dagang Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096250","display_name":"Beijing Institute of Big Data Research","ror":"https://ror.org/00s1sz824","country_code":"CN","type":"facility","lineage":["https://openalex.org/I20231570","https://openalex.org/I37796252","https://openalex.org/I4210096250"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dagang Chen","raw_affiliation_strings":["CETC Big Data Research Institute Co., Ltd., Guiyang, China"],"affiliations":[{"raw_affiliation_string":"CETC Big Data Research Institute Co., Ltd., Guiyang, China","institution_ids":["https://openalex.org/I4210096250"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5075261068"],"corresponding_institution_ids":["https://openalex.org/I4210096250"],"apc_list":null,"apc_paid":null,"fwci":0.7001,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.77429552,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"121","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9962999820709229,"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":0.9962999820709229,"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":0.9715999960899353,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9678999781608582,"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":0.8414714336395264},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.6976547837257385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6151070594787598},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5806753039360046},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.5491625070571899},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5150485038757324},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5120139718055725},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46049195528030396},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.45295441150665283},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4450661838054657},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4182487726211548},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.332186222076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8414714336395264},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.6976547837257385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6151070594787598},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5806753039360046},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5491625070571899},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5150485038757324},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5120139718055725},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46049195528030396},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.45295441150665283},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4450661838054657},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4182487726211548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.332186222076416},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3319921.3319970","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319921.3319970","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2019 3rd International Conference on Innovation in Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1978394996","https://openalex.org/W2004915807","https://openalex.org/W2099111195","https://openalex.org/W2118020653","https://openalex.org/W2120615054","https://openalex.org/W2126502509","https://openalex.org/W2131744502","https://openalex.org/W2140785063","https://openalex.org/W2252223413","https://openalex.org/W2265846598","https://openalex.org/W2295598076","https://openalex.org/W2470673105","https://openalex.org/W2610930722","https://openalex.org/W2740333758","https://openalex.org/W2911964244","https://openalex.org/W2919115771","https://openalex.org/W2920184902","https://openalex.org/W2949300694","https://openalex.org/W3102476541","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"In":[0],"China,":[1,28,73],"the":[2,16,22,37,40,74,113,133,141,153],"government":[3,19,29,75,114,128],"documents":[4,6],"are":[5,50,107],"with":[7],"legal":[8],"effect":[9],"and":[10,68],"of":[11,18,25,39],"standard":[12],"forms":[13],"formulated":[14],"in":[15,27,72],"process":[17],"administration.":[20],"With":[21],"continuous":[23],"development":[24],"e-government":[26],"database":[30],"size":[31],"increases":[32],"hugely.":[33],"To":[34],"fully":[35],"utilize":[36],"potential":[38],"database,":[41],"many":[42,58],"applications":[43,60],"based":[44,80,91,131],"on":[45,81,92,101,112,132,146,157],"natural":[46],"language":[47],"processing":[48],"(NLP)":[49],"developed.":[51],"Classification":[52],"is":[53],"a":[54,118],"fundamental":[55],"task":[56],"for":[57,127],"NLP":[59],"such":[61],"as":[62],"automatic":[63],"document":[64,76,129],"archive,":[65],"intelligent":[66],"search,":[67],"personalized":[69],"recommendation.":[70],"Presently,":[71],"classification":[77,130,143],"method":[78,119,155],"which":[79],"issuing":[82],"departments":[83],"has":[84],"very":[85],"low":[86],"accuracy.":[87],"Traditional":[88],"text":[89],"classifiers":[90],"machine":[93],"learning":[94,97],"or":[95],"deep":[96],"models":[98],"rely":[99],"heavily":[100],"human-labeled":[102],"training":[103],"data.":[104],"While":[105],"there":[106],"no":[108],"open":[109],"data":[110,125,150],"sets":[111],"documents,":[115],"we":[116],"propose":[117],"to":[120],"automatically":[121,148],"constructing":[122],"large-scale":[123],"annotated":[124],"set":[126,151],"information":[134],"retrieval":[135],"method.":[136],"Experiment":[137],"results":[138],"show":[139],"that":[140],"supervised":[142],"model":[144],"trained":[145],"our":[147],"constructed":[149],"outperforms":[152],"baseline":[154],"15%":[156],"F1-score.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}