{"id":"https://openalex.org/W4392445408","doi":"https://doi.org/10.1145/3639233.3639341","title":"TF-NERD: Tagalog Fine-grained Named Entity Recognition Dataset","display_name":"TF-NERD: Tagalog Fine-grained Named Entity Recognition Dataset","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4392445408","doi":"https://doi.org/10.1145/3639233.3639341"},"language":"en","primary_location":{"id":"doi:10.1145/3639233.3639341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639233.3639341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval","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/A5102749459","display_name":"Robin Kamille Ramos","orcid":"https://orcid.org/0009-0007-9149-6820"},"institutions":[{"id":"https://openalex.org/I19722","display_name":"Ateneo de Manila University","ror":"https://ror.org/053kevk63","country_code":"PH","type":"education","lineage":["https://openalex.org/I19722"]}],"countries":["PH"],"is_corresponding":true,"raw_author_name":"Robin Kamille Ramos","raw_affiliation_strings":["Department of Information Systems and Computer Science, Ateneo de Manila University, Philippines"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems and Computer Science, Ateneo de Manila University, Philippines","institution_ids":["https://openalex.org/I19722"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003478603","display_name":"John Paul C. Vergara","orcid":"https://orcid.org/0000-0003-0041-4847"},"institutions":[{"id":"https://openalex.org/I19722","display_name":"Ateneo de Manila University","ror":"https://ror.org/053kevk63","country_code":"PH","type":"education","lineage":["https://openalex.org/I19722"]}],"countries":["PH"],"is_corresponding":false,"raw_author_name":"John Paul Vergara","raw_affiliation_strings":["Department of Information Systems and Computer Science, Ateneo de Manila University, Philippines"],"affiliations":[{"raw_affiliation_string":"Department of Information Systems and Computer Science, Ateneo de Manila University, Philippines","institution_ids":["https://openalex.org/I19722"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102749459"],"corresponding_institution_ids":["https://openalex.org/I19722"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20823718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"222","last_page":"227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994000196456909,"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":0.9660000205039978,"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":0.8715864419937134},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.8523563742637634},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6694775223731995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6131637096405029},{"id":"https://openalex.org/keywords/named-entity","display_name":"Named entity","score":0.5320860743522644},{"id":"https://openalex.org/keywords/entity-linking","display_name":"Entity linking","score":0.4876209795475006},{"id":"https://openalex.org/keywords/phrase","display_name":"Phrase","score":0.48652973771095276},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.44863033294677734},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.34996500611305237},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.08260396122932434}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8715864419937134},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.8523563742637634},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6694775223731995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6131637096405029},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.5320860743522644},{"id":"https://openalex.org/C96711827","wikidata":"https://www.wikidata.org/wiki/Q17012245","display_name":"Entity linking","level":3,"score":0.4876209795475006},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.48652973771095276},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.44863033294677734},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.34996500611305237},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.08260396122932434},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639233.3639341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639233.3639341","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval","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":5,"referenced_works":["https://openalex.org/W2333820424","https://openalex.org/W2742113707","https://openalex.org/W2897024748","https://openalex.org/W3208594153","https://openalex.org/W4313161663"],"related_works":["https://openalex.org/W2186562580","https://openalex.org/W2032007337","https://openalex.org/W4255258373","https://openalex.org/W2593907245","https://openalex.org/W2155874911","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":[1,122,132],"recognition":[2],"(NER)":[3],"is":[4],"a":[5,30,40],"crucial":[6],"foundational":[7],"step":[8],"in":[9,50],"information":[10],"extraction.":[11],"This":[12],"research":[13],"aims":[14],"to":[15,86],"improve":[16],"existing":[17],"natural":[18],"language":[19,26,111],"processing":[20],"(NLP)":[21],"resources":[22],"for":[23,95,121,131],"the":[24,88,93,101,103,108],"low-resource":[25],"Tagalog":[27,51],"by":[28],"constructing":[29],"human-annotated":[31],"NER":[32,42,81,97,104],"dataset.":[33],"In":[34],"this":[35],"paper,":[36],"we":[37],"present":[38],"TF-NERD,":[39],"fine-grained":[41],"dataset":[43,94],"that":[44],"consists":[45],"of":[46,92],"2,337":[47],"paragraphs":[48],"written":[49],"and":[52,77,90,118,125,128],"scraped":[53],"from":[54],"various":[55],"internet":[56],"sources.":[57],"These":[58],"entities":[59],"are":[60],"classified":[61],"into":[62],"12":[63],"categories":[64],"-":[65],"art,":[66],"event,":[67],"facility,":[68],"geo-political,":[69],"language,":[70],"law,":[71],"location,":[72],"nationalities,":[73],"organization,":[74],"person,":[75],"product,":[76],"other":[78],"entities.":[79],"Benchmark":[80],"transformer":[82],"models":[83],"were":[84],"constructed":[85],"assess":[87],"quality":[89],"usability":[91],"future":[96],"research.":[98],"Based":[99],"on":[100],"results,":[102],"model":[105,112],"finetuned":[106],"with":[107,115],"pretrained":[109],"roBERTa":[110],"performed":[113],"best":[114],"82.31%":[116],"recall":[117,127],"80.67%":[119],"precision":[120,130],"type":[123],"classification,":[124],"88.02%":[126],"86.27%":[129],"phrase":[133],"identification.":[134]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}