{"id":"https://openalex.org/W3124763565","doi":"https://doi.org/10.1145/3428757.3429142","title":"Mitigating Effect of Dictionary Matching Errors in Distantly Supervised Named Entity Recognition","display_name":"Mitigating Effect of Dictionary Matching Errors in Distantly Supervised Named Entity Recognition","publication_year":2020,"publication_date":"2020-11-30","ids":{"openalex":"https://openalex.org/W3124763565","doi":"https://doi.org/10.1145/3428757.3429142","mag":"3124763565"},"language":"en","primary_location":{"id":"doi:10.1145/3428757.3429142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","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/A5007699713","display_name":"Koga Kobayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koga Kobayashi","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Ibaraki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100887101","display_name":"Kei Wakabayashi","orcid":null},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kei Wakabayashi","raw_affiliation_strings":["University of Tsukuba, Tsukuba, Ibaraki, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Tsukuba, Ibaraki, Japan","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18794878,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"114"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9984999895095825,"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":0.9804999828338623,"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":0.9344358444213867},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8132914304733276},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6687000393867493},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.6016161441802979},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5779974460601807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5727883577346802},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.547620952129364},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.5388768315315247},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.46349334716796875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3749958872795105},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.13519224524497986},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.118539959192276},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.09318035840988159}],"concepts":[{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.9344358444213867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132914304733276},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6687000393867493},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.6016161441802979},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5779974460601807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5727883577346802},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.547620952129364},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.5388768315315247},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.46349334716796875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3749958872795105},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.13519224524497986},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.118539959192276},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.09318035840988159},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3428757.3429142","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3428757.3429142","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd International Conference on Information Integration and Web-based Applications & Services","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G6294233638","display_name":"Study on Improving Performance of Natural Language Processing by Integrating Collocation Extraction and Deep Learning","funder_award_id":"19K20333","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2296283641","https://openalex.org/W2891383691","https://openalex.org/W2945214158","https://openalex.org/W2953010755","https://openalex.org/W2962987552"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W2155874911","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W2032007337","https://openalex.org/W3000685722","https://openalex.org/W1884363728","https://openalex.org/W4253099099","https://openalex.org/W4386977977","https://openalex.org/W4200491110"],"abstract_inverted_index":{"Named":[0],"entity":[1,40],"recognition":[2],"(NER)":[3],"is":[4,42],"a":[5,23,31,46,58],"fundamental":[6],"technique":[7],"that":[8,37,63,102],"brings":[9],"basic":[10],"semantic":[11],"awareness":[12],"to":[13,29,44,49,77],"natural":[14],"language":[15],"processing":[16],"applications":[17],"and":[18,67,74],"services.":[19],"Since":[20],"we":[21,75,84],"need":[22,76],"large":[24],"amount":[25],"of":[26,61,69,90,110],"training":[27],"data":[28],"train":[30,50],"custom":[32],"NER":[33,51,72,91],"model,":[34],"distant":[35],"supervision":[36],"leverages":[38],"named":[39],"dictionaries":[41],"expected":[43],"be":[45],"promising":[47],"approach":[48],"models":[52,92],"quickly.":[53],"However,":[54],"dictionary":[55,96,115],"matching":[56,97],"causes":[57],"considerable":[59],"number":[60],"errors":[62],"deteriorates":[64],"both":[65],"precision":[66,89],"recall":[68],"the":[70,103],"final":[71],"models,":[73],"mitigate":[78],"its":[79],"effect.":[80],"In":[81],"this":[82],"study,":[83],"particularly":[85],"aim":[86],"at":[87],"improving":[88],"by":[93],"accounting":[94],"for":[95],"errors.":[98],"Experimental":[99],"results":[100],"show":[101],"proposed":[104],"method":[105],"can":[106],"achieve":[107],"an":[108],"improvement":[109],"precisions":[111],"especially":[112],"under":[113],"poor":[114],"performance":[116],"conditions.":[117]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}