{"id":"https://openalex.org/W82340936","doi":null,"title":"Morphological features help POS tagging of unknown words across language varieties.","display_name":"Morphological features help POS tagging of unknown words across language varieties.","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W82340936","mag":"82340936"},"language":"en","primary_location":{"id":"mag:82340936","doi":null,"is_oa":false,"landing_page_url":"http://nlp.stanford.edu/manning/papers/sighan_pos.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5041717466","display_name":"Huihsin Tseng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huihsin Tseng","raw_affiliation_strings":["University of Colorado \u2010 Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado \u2010 Boulder","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036266399","display_name":"Daniel S. Jurafsky","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Jurafsky","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X","observed_orcids":["https://orcid.org/0000-0001-6155-649X"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher D. Manning","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.3436,"has_fulltext":false,"cited_by_count":93,"citation_normalized_percentile":{"value":0.93878051,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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/part-of-speech-tagging","display_name":"part-of-speech tagging","score":0.9980000257492065},{"id":"https://openalex.org/keywords/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.8809999823570251},{"id":"https://openalex.org/keywords/morphological-features","display_name":"morphological features","score":0.7239999771118164},{"id":"https://openalex.org/keywords/taiwanese-mandarin","display_name":"Taiwan Mandarin","score":0.8740000128746033},{"id":"https://openalex.org/keywords/maximum-entropy-markov-model","display_name":"maximum entropy Markov model","score":0.9200000166893005}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7888463735580444},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.691650927066803},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6630421876907349},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6628467440605164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6328901052474976},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.6245916485786438},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.570552408695221},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44432199001312256},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4246678054332733},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4054921865463257},{"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":"mag:82340936","doi":null,"is_oa":false,"landing_page_url":"http://nlp.stanford.edu/manning/papers/sighan_pos.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W76271513","https://openalex.org/W1575907248","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1934019294","https://openalex.org/W1996430422","https://openalex.org/W2000566875","https://openalex.org/W2056321066","https://openalex.org/W2135843243","https://openalex.org/W2155280192","https://openalex.org/W2425667873","https://openalex.org/W3200634688"],"related_works":["https://openalex.org/W2049485229","https://openalex.org/W2247874908","https://openalex.org/W7098376246","https://openalex.org/W2243475059","https://openalex.org/W2408487574","https://openalex.org/W80748239","https://openalex.org/W2103374253","https://openalex.org/W1855497951","https://openalex.org/W174553219","https://openalex.org/W7097219626"],"abstract_inverted_index":{"Part-of-speech":[0],"tagging,":[1,127,157],"like":[2,108],"any":[3],"supervised":[4],"statistical":[5],"NLP":[6],"task,":[7],"is":[8,106],"more":[9,107],"difficult":[10],"when":[11,22],"test":[12],"sets":[13],"are":[14,91],"very":[15],"different":[16,37],"from":[17,170],"training":[18],"sets,":[19],"for":[20,125],"example":[21],"tagging":[23,35,135,161],"across":[24],"genres":[25],"or":[26],"language":[27],"varieties.":[28],"We":[29,87],"examined":[30],"the":[31,94],"problem":[32],"of":[33,36,39,59,97,120],"POS":[34,126],"varieties":[38,165],"Mandarin":[40,78,105,156],"Chinese":[41,167],"(PRC-Mainland,":[42],"PRCHong":[43],"Kong,":[44],"and":[45,85,138],"Taiwan).":[46],"An":[47],"analytic":[48],"study":[49],"first":[50],"showed":[51,88],"that":[52,77],"unknown":[53,79],"words":[54,65,80],"were":[55,81,142],"a":[56,118,145],"major":[57],"source":[58],"difficulty":[60],"in":[61,66,100,102,136,144,155,166],"cross-variety":[62],"tagging.":[63],"Unknown":[64],"English":[67,137],"tend":[68],"to":[69,172],"be":[70],"proper":[71],"nouns.":[72],"By":[73],"contrast,":[74],"we":[75,116],"found":[76],"mostly":[82],"common":[83],"nouns":[84],"verbs.":[86],"these":[89],"results":[90],"caused":[92],"by":[93,131],"high":[95],"frequency":[96],"morphological":[98,122],"compounding":[99],"Mandarin;":[101],"this":[103,114],"sense":[104],"German":[109],"than":[110],"English.":[111],"Based":[112],"on":[113,133,163],"analysis,":[115],"propose":[117],"variety":[119],"new":[121],"unknown-word":[123,134,160],"features":[124,141],"extending":[128],"earlier":[129],"work":[130],"others":[132],"German.":[139],"Our":[140,150],"implemented":[143],"maximum":[146],"entropy":[147],"Markov":[148],"model.":[149],"system":[151],"achieves":[152],"state-of-the-art":[153],"performance":[154,162],"including":[158],"improving":[159],"unseen":[164],"Treebank":[168],"5.0":[169],"61%":[171],"80%":[173],"correct.":[174]},"counts_by_year":[{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":5}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2016-06-24T00:00:00"}