{"id":"https://openalex.org/W2790360088","doi":"https://doi.org/10.1109/ialp.2017.8300608","title":"Mining features for web ner model construction based on distant learning","display_name":"Mining features for web ner model construction based on distant learning","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2790360088","doi":"https://doi.org/10.1109/ialp.2017.8300608","mag":"2790360088"},"language":"en","primary_location":{"id":"doi:10.1109/ialp.2017.8300608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2017.8300608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Asian Language Processing (IALP)","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/A5113786835","display_name":"Chien-Lung Chou","orcid":null},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Lung Chou","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078524542","display_name":"Chia\u2010Hui Chang","orcid":"https://orcid.org/0000-0002-1101-6337"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Hui Chang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.19739266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"31","issue":null,"first_page":"322","last_page":"325"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.998199999332428,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9965999722480774,"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/named-entity-recognition","display_name":"Named-entity recognition","score":0.8873274922370911},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8231135606765747},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.7677468061447144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.579097330570221},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5743122100830078},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.5737943053245544},{"id":"https://openalex.org/keywords/labelling","display_name":"Labelling","score":0.5152085423469543},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4866269528865814},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4853340685367584},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.4172067940235138},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.06896942853927612},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06648924946784973}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8873274922370911},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8231135606765747},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.7677468061447144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.579097330570221},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5743122100830078},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.5737943053245544},{"id":"https://openalex.org/C2780523633","wikidata":"https://www.wikidata.org/wiki/Q380709","display_name":"Labelling","level":2,"score":0.5152085423469543},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4866269528865814},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4853340685367584},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.4172067940235138},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.06896942853927612},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06648924946784973},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp.2017.8300608","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp.2017.8300608","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W2078527501","https://openalex.org/W2088101210","https://openalex.org/W2096765155","https://openalex.org/W2107598941","https://openalex.org/W2110219039","https://openalex.org/W2133556223","https://openalex.org/W2147707543","https://openalex.org/W2147717514","https://openalex.org/W2149167588","https://openalex.org/W2159874616","https://openalex.org/W2181852421","https://openalex.org/W2399438596","https://openalex.org/W2530283981","https://openalex.org/W4285719527","https://openalex.org/W6676342170","https://openalex.org/W6712578843"],"related_works":["https://openalex.org/W2032007337","https://openalex.org/W2186562580","https://openalex.org/W4399418584","https://openalex.org/W189110383","https://openalex.org/W2945210837","https://openalex.org/W2155874911","https://openalex.org/W2530283981","https://openalex.org/W2589080577","https://openalex.org/W3036779180","https://openalex.org/W4224941621"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,76],"study":[4],"the":[5,18,53,93,129,136],"problem":[6],"of":[7,55,81,95,111,124],"developing":[8],"a":[9,78],"WIDM":[10],"NER":[11,46,139],"tool":[12],"to":[13,127],"prepare":[14],"training":[15,44,57],"corpus":[16],"from":[17,59],"Web":[19,138],"for":[20,43,102],"custom":[21],"named":[22],"entity":[23,112],"recognition":[24,113],"(NER)":[25],"models":[26,47],"via":[27,48,62],"distant":[28],"learning.":[29,104],"We":[30,105],"consider":[31],"two":[32],"major":[33],"issues":[34],"including":[35,114],"efficient":[36,69],"automatic":[37,70],"labelling":[38,50,71],"and":[39,85,122,133],"effective":[40],"feature":[41],"mining":[42,94],"accurate":[45],"sequence":[49],"technique.":[51],"While":[52],"idea":[54],"collecting":[56],"sentences":[58,86],"search":[60],"snippets":[61],"known":[63],"entities":[64],"(seeds)":[65],"is":[66],"not":[67],"new,":[68],"becomes":[72],"an":[73],"issue":[74,91],"when":[75],"have":[77],"large":[79],"number":[80],"seeds":[82],"(e.g.":[83,87],"500K)":[84],"2M).":[88],"The":[89],"second":[90],"regards":[92],"interesting":[96],"terms":[97],"or":[98],"k-grams":[99],"as":[100],"features":[101],"supervised":[103],"conduct":[106],"experiments":[107],"on":[108],"four":[109],"types":[110],"Chinese":[115],"person":[116],"name,":[117,119,121],"food":[118],"location":[120],"point":[123],"interest":[125],"(POI)":[126],"demonstrate":[128],"improvement":[130],"in":[131],"efficiency":[132],"effectiveness":[134],"with":[135],"proposed":[137],"model":[140],"construction":[141],"tool.":[142]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}