{"id":"https://openalex.org/W2963837895","doi":"https://doi.org/10.18653/v1/n16-1157","title":"Part-of-Speech Tagging for Historical English","display_name":"Part-of-Speech Tagging for Historical English","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2963837895","doi":"https://doi.org/10.18653/v1/n16-1157","mag":"2963837895"},"language":"en","primary_location":{"id":"doi:10.18653/v1/n16-1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1157","pdf_url":"https://www.aclweb.org/anthology/N16-1157.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/N16-1157.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100657571","display_name":"Yi Yang","orcid":"https://orcid.org/0000-0002-3021-0522"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Yang","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology Atlanta, GA 30308"],"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology Atlanta, GA 30308","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047699861","display_name":"Jacob Eisenstein","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jacob Eisenstein","raw_affiliation_strings":["School of Interactive Computing Georgia Institute of Technology Atlanta, GA 30308"],"affiliations":[{"raw_affiliation_string":"School of Interactive Computing Georgia Institute of Technology Atlanta, GA 30308","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100657571"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":9.2761,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.97952546,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1318","last_page":"1328"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/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/T13629","display_name":"Text Readability and Simplification","score":0.9868999719619751,"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":0.8449580669403076},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7076914310455322},{"id":"https://openalex.org/keywords/spelling","display_name":"Spelling","score":0.6513851881027222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6430795788764954},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5871466994285583},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.5320134162902832},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5250049829483032},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5244629383087158},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.500443696975708},{"id":"https://openalex.org/keywords/lemmatisation","display_name":"Lemmatisation","score":0.4732951521873474},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.46658995747566223},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4303530752658844},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41177991032600403},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37192314863204956},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2838760018348694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8449580669403076},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7076914310455322},{"id":"https://openalex.org/C2777801307","wikidata":"https://www.wikidata.org/wiki/Q2088390","display_name":"Spelling","level":2,"score":0.6513851881027222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6430795788764954},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5871466994285583},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.5320134162902832},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5250049829483032},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5244629383087158},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.500443696975708},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.4732951521873474},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.46658995747566223},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4303530752658844},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41177991032600403},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37192314863204956},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2838760018348694},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/n16-1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1157","pdf_url":"https://www.aclweb.org/anthology/N16-1157.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/n16-1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/n16-1157","pdf_url":"https://www.aclweb.org/anthology/N16-1157.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 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8299999833106995,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2446927264","display_name":"EAGER: Exploring Adapting Language Technology Across a Network of Domains","funder_award_id":"1349837","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3611247453","display_name":null,"funder_award_id":"R01GM","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G4212936320","display_name":null,"funder_award_id":"R01GM112697","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5485584296","display_name":null,"funder_award_id":"R01GM112697-01","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963837895.pdf","grobid_xml":"https://content.openalex.org/works/W2963837895.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W14873975","https://openalex.org/W22792603","https://openalex.org/W70524345","https://openalex.org/W121769347","https://openalex.org/W205969848","https://openalex.org/W582714233","https://openalex.org/W1553878378","https://openalex.org/W1570098300","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1824916146","https://openalex.org/W1882958252","https://openalex.org/W1993727539","https://openalex.org/W1996430422","https://openalex.org/W2093366816","https://openalex.org/W2096873754","https://openalex.org/W2101234009","https://openalex.org/W2101761627","https://openalex.org/W2104094955","https://openalex.org/W2104936489","https://openalex.org/W2105523772","https://openalex.org/W2106279089","https://openalex.org/W2111362445","https://openalex.org/W2120354757","https://openalex.org/W2121227244","https://openalex.org/W2123442489","https://openalex.org/W2138238723","https://openalex.org/W2141034612","https://openalex.org/W2152148513","https://openalex.org/W2153579005","https://openalex.org/W2158108973","https://openalex.org/W2158139315","https://openalex.org/W2158359079","https://openalex.org/W2182077928","https://openalex.org/W2214409633","https://openalex.org/W2247982316","https://openalex.org/W2251732921","https://openalex.org/W2399720833","https://openalex.org/W2949821452","https://openalex.org/W2962755455","https://openalex.org/W2963826681","https://openalex.org/W3146885639","https://openalex.org/W4210706177","https://openalex.org/W4294170691"],"related_works":["https://openalex.org/W2100947578","https://openalex.org/W2161008081","https://openalex.org/W1555832326","https://openalex.org/W4298186509","https://openalex.org/W2556702969","https://openalex.org/W2887281027","https://openalex.org/W217221262","https://openalex.org/W611030372","https://openalex.org/W4393539582","https://openalex.org/W2574766132"],"abstract_inverted_index":{"As":[0],"more":[1],"historical":[2,44,73],"texts":[3,102],"are":[4,37],"digitized,":[5],"there":[6],"is":[7,24,157],"interest":[8],"in":[9,54,103,165],"applying":[10],"natural":[11],"language":[12,29],"processing":[13],"tools":[14,23],"to":[15,28,50,70],"these":[16,22],"archives.":[17],"However,":[18],"the":[19,38,64,77,91,104,113,128,132,151,154],"performance":[20,146],"of":[21,66,81,93,107,130,153],"often":[25],"unsatisfactory,":[26],"due":[27],"change":[30],"and":[31,56,98,124],"genre":[32],"differences.":[33],"Spelling":[34],"normalization":[35],"heuristics":[36],"dominant":[39],"solution":[40],"for":[41,52,117],"dealing":[42],"with":[43,72],"texts,":[45,74],"but":[46,150],"this":[47,59],"approach":[48],"fails":[49],"account":[51],"changes":[53],"usage":[55],"vocabulary.":[57],"In":[58],"empirical":[60],"paper,":[61],"we":[62],"assess":[63],"capability":[65],"domain":[67,87,119],"adaptation":[68,88,120],"techniques":[69],"cope":[71],"focusing":[75],"on":[76,90,168],"classic":[78],"benchmark":[79],"task":[80,92],"part-of-speech":[82],"tagging.":[83],"We":[84,110],"evaluate":[85],"several":[86],"methods":[89,156],"tagging":[94,166],"Early":[95,169],"Modern":[96,99,170],"English":[97,101,171],"British":[100],"Penn":[105],"Corpora":[106],"Historical":[108],"English.":[109],"demonstrate":[111],"that":[112],"Feature":[114,141],"Embedding":[115],"method":[116],"unsupervised":[118],"outperforms":[121],"word":[122],"embeddings":[123],"Brown":[125],"clusters,":[126],"showing":[127],"importance":[129],"embedding":[131],"entire":[133],"feature":[134],"space,":[135],"rather":[136],"than":[137,147],"just":[138],"individual":[139],"words.":[140],"Embeddings":[142],"also":[143],"give":[144],"better":[145,158],"spelling":[148],"normalization,":[149],"combination":[152],"two":[155],"still,":[159],"yielding":[160],"a":[161],"5%":[162],"raw":[163],"improvement":[164],"accuracy":[167],"texts.":[172]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}