{"id":"https://openalex.org/W3115908473","doi":"https://doi.org/10.18653/v1/2020.coling-main.343","title":"An Analysis of Simple Data Augmentation for Named Entity Recognition","display_name":"An Analysis of Simple Data Augmentation for Named Entity Recognition","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3115908473","doi":"https://doi.org/10.18653/v1/2020.coling-main.343","mag":"3115908473"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2020.coling-main.343","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.343","pdf_url":"https://aclanthology.org/2020.coling-main.343.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2020.coling-main.343.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101585101","display_name":"Xiang Dai","orcid":"https://orcid.org/0000-0002-6020-9688"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"government","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]},{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["AU","DE"],"is_corresponding":true,"raw_author_name":"Xiang Dai","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany","University of Sydney, Sydney, Australia","CSIRO Data61, Sydney, Australia"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]},{"raw_affiliation_string":"University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]},{"raw_affiliation_string":"CSIRO Data61, Sydney, Australia","institution_ids":["https://openalex.org/I42894916","https://openalex.org/I1292875679"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055589412","display_name":"Heike Adel","orcid":"https://orcid.org/0000-0003-2787-0084"},"institutions":[{"id":"https://openalex.org/I889804353","display_name":"Robert Bosch (Germany)","ror":"https://ror.org/01fe0jt45","country_code":"DE","type":"company","lineage":["https://openalex.org/I889804353"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Heike Adel","raw_affiliation_strings":["Bosch Center for Artificial Intelligence, Renningen, Germany"],"affiliations":[{"raw_affiliation_string":"Bosch Center for Artificial Intelligence, Renningen, Germany","institution_ids":["https://openalex.org/I889804353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101585101"],"corresponding_institution_ids":["https://openalex.org/I1292875679","https://openalex.org/I129604602","https://openalex.org/I42894916","https://openalex.org/I889804353"],"apc_list":null,"apc_paid":null,"fwci":17.6953,"has_fulltext":true,"cited_by_count":179,"citation_normalized_percentile":{"value":0.9939374,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3861","last_page":"3867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T13629","display_name":"Text Readability and Simplification","score":0.9951000213623047,"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":0.8280475735664368},{"id":"https://openalex.org/keywords/named-entity-recognition","display_name":"Named-entity recognition","score":0.7260901927947998},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7246699333190918},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.720855712890625},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.677507758140564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5397966504096985},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5395888686180115},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.538987934589386},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.5113970637321472},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4470064640045166},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3365786671638489},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07293978333473206}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280475735664368},{"id":"https://openalex.org/C2779135771","wikidata":"https://www.wikidata.org/wiki/Q403574","display_name":"Named-entity recognition","level":3,"score":0.7260901927947998},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7246699333190918},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.720855712890625},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.677507758140564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5397966504096985},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5395888686180115},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.538987934589386},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.5113970637321472},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4470064640045166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3365786671638489},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07293978333473206},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2020.coling-main.343","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.343","pdf_url":"https://aclanthology.org/2020.coling-main.343.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2020.coling-main.343","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2020.coling-main.343","pdf_url":"https://aclanthology.org/2020.coling-main.343.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th International Conference on Computational Linguistics","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3115908473.pdf","grobid_xml":"https://content.openalex.org/works/W3115908473.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1840435438","https://openalex.org/W2131546905","https://openalex.org/W2143612262","https://openalex.org/W2168041406","https://openalex.org/W2170240176","https://openalex.org/W2250473257","https://openalex.org/W2250539671","https://openalex.org/W2251658415","https://openalex.org/W2516907570","https://openalex.org/W2775795276","https://openalex.org/W2888519496","https://openalex.org/W2892131163","https://openalex.org/W2896457183","https://openalex.org/W2905266130","https://openalex.org/W2942203175","https://openalex.org/W2946068894","https://openalex.org/W2951476960","https://openalex.org/W2953173959","https://openalex.org/W2962721878","https://openalex.org/W2963012544","https://openalex.org/W2963047838","https://openalex.org/W2963126845","https://openalex.org/W2963341956","https://openalex.org/W2963526187","https://openalex.org/W2963545917","https://openalex.org/W2963564796","https://openalex.org/W2964046515","https://openalex.org/W2964120993","https://openalex.org/W2966049804","https://openalex.org/W2970771982","https://openalex.org/W2971116422","https://openalex.org/W2971296908","https://openalex.org/W2979736514","https://openalex.org/W3034238904","https://openalex.org/W3034949140","https://openalex.org/W3035282664","https://openalex.org/W3035352537","https://openalex.org/W3090789254","https://openalex.org/W3098341425","https://openalex.org/W4295253143"],"related_works":["https://openalex.org/W4322096459","https://openalex.org/W189110383","https://openalex.org/W2589080577","https://openalex.org/W4379251483","https://openalex.org/W4321523623","https://openalex.org/W3161409692","https://openalex.org/W2530283981","https://openalex.org/W4287197350","https://openalex.org/W3036779180","https://openalex.org/W3047727388"],"abstract_inverted_index":{"Simple":[0],"yet":[1],"effective":[2],"data":[3,25,45],"augmentation":[4,26,61],"techniques":[5],"have":[6],"been":[7],"proposed":[8],"for":[9,27,65,72],"sentence-level":[10],"and":[11,23,50,55,68],"sentence-pair":[12],"natural":[13],"language":[14],"processing":[15],"tasks.":[16],"Inspired":[17],"by":[18],"these":[19],"efforts,":[20],"we":[21,57],"design":[22],"compare":[24],"named":[28],"entity":[29],"recognition,":[30],"which":[31],"is":[32],"usually":[33],"modeled":[34],"as":[35],"a":[36],"token-level":[37],"sequence":[38],"labeling":[39],"problem.":[40],"Through":[41],"experiments":[42],"on":[43],"two":[44],"sets":[46],"from":[47],"the":[48],"biomedical":[49],"materials":[51],"science":[52],"domains":[53],"(i2b2-2010":[54],"MaSciP),":[56],"show":[58],"that":[59],"simple":[60],"can":[62],"boost":[63],"performance":[64],"both":[66],"recurrent":[67],"transformer-based":[69],"models,":[70],"especially":[71],"small":[73],"training":[74],"sets.":[75]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":48},{"year":2022,"cited_by_count":37},{"year":2021,"cited_by_count":44}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}