{"id":"https://openalex.org/W2250297702","doi":"https://doi.org/10.18653/v1/d15-1211","title":"A Transition-based Model for Joint Segmentation, POS-tagging and Normalization","display_name":"A Transition-based Model for Joint Segmentation, POS-tagging and Normalization","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250297702","doi":"https://doi.org/10.18653/v1/d15-1211","mag":"2250297702"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d15-1211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1211","pdf_url":"https://www.aclweb.org/anthology/D15-1211.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D15-1211.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035133018","display_name":"Qian Tao","orcid":"https://orcid.org/0000-0002-8416-7224"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]},{"id":"https://openalex.org/I4210101555","display_name":"Hubei University of Science and Technology","ror":"https://ror.org/018wg9441","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210101555"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Qian","raw_affiliation_strings":["College of Computer Science and Technology, Hubei University of Science and Technology, XianNing, China","Computer School, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Hubei University of Science and Technology, XianNing, China","institution_ids":["https://openalex.org/I4210101555"]},{"raw_affiliation_string":"Computer School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333729","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0002-5214-2268"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004953265","display_name":"Meishan Zhang","orcid":"https://orcid.org/0000-0001-6335-1340"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meishan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055938662","display_name":"Yafeng Ren","orcid":"https://orcid.org/0000-0002-0291-4733"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]},{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Yafeng Ren","raw_affiliation_strings":["Computer School, Wuhan University, Wuhan, China","Singapore University of Technology and Design"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"Singapore University of Technology and Design","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058877618","display_name":"Donghong Ji","orcid":"https://orcid.org/0000-0001-9613-5927"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghong Ji","raw_affiliation_strings":["Computer School, Wuhan University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer School, Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1837","last_page":"1846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/microblogging","display_name":"Microblogging","score":0.8832987546920776},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8161343336105347},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7990325093269348},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.746288001537323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6648153066635132},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.6198610067367554},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.6107786297798157},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5794373750686646},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.5530873537063599},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4112117886543274},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35781383514404297},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.07749795913696289},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.058409929275512695}],"concepts":[{"id":"https://openalex.org/C143275388","wikidata":"https://www.wikidata.org/wiki/Q92438","display_name":"Microblogging","level":3,"score":0.8832987546920776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161343336105347},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7990325093269348},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.746288001537323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6648153066635132},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.6198610067367554},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.6107786297798157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5794373750686646},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.5530873537063599},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4112117886543274},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35781383514404297},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.07749795913696289},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.058409929275512695},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/d15-1211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1211","pdf_url":"https://www.aclweb.org/anthology/D15-1211.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.697.4575","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.697.4575","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://aclweb.org/anthology/D/D15/D15-1211.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/v1/d15-1211","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d15-1211","pdf_url":"https://www.aclweb.org/anthology/D15-1211.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 2015 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G3899392129","display_name":"\u6c49\u8bed\u8bed\u7bc7\u8fde\u8d2f\u7684\u4e8b\u4ef6\u94fe\u6a21\u578b\u7814\u7a76","funder_award_id":"61373108","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3992338163","display_name":"\u57fa\u4e8e\u6982\u7387\u4e3b\u9898\u6a21\u578b\u7684\u8bcd\u4e49\u8ba1\u7b97\u53ca\u5e94\u7528\u7814\u7a76","funder_award_id":"61373056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6841785368","display_name":null,"funder_award_id":"61133012","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250297702.pdf","grobid_xml":"https://content.openalex.org/works/W2250297702.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W63056884","https://openalex.org/W86604388","https://openalex.org/W157541337","https://openalex.org/W169290101","https://openalex.org/W1586073462","https://openalex.org/W1604437366","https://openalex.org/W1728658630","https://openalex.org/W2010595692","https://openalex.org/W2011902273","https://openalex.org/W2055828199","https://openalex.org/W2100237474","https://openalex.org/W2103275845","https://openalex.org/W2104820387","https://openalex.org/W2110974939","https://openalex.org/W2116983617","https://openalex.org/W2133503566","https://openalex.org/W2137766873","https://openalex.org/W2146867136","https://openalex.org/W2152374779","https://openalex.org/W2157765050","https://openalex.org/W2158061377","https://openalex.org/W2163942301","https://openalex.org/W2165664509","https://openalex.org/W2172221237","https://openalex.org/W2250174865","https://openalex.org/W2250542158","https://openalex.org/W2250623963","https://openalex.org/W2251362855","https://openalex.org/W2251380531","https://openalex.org/W2251404146","https://openalex.org/W2251922156","https://openalex.org/W2252225757","https://openalex.org/W2397927934","https://openalex.org/W4233787372"],"related_works":["https://openalex.org/W2172629291","https://openalex.org/W2380773642","https://openalex.org/W2384559435","https://openalex.org/W2337707338","https://openalex.org/W2393940967","https://openalex.org/W2159591557","https://openalex.org/W2785359773","https://openalex.org/W2058548953","https://openalex.org/W2385598138","https://openalex.org/W2366925922"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"transition-based":[3],"model":[4,19,52],"for":[5],"joint":[6,51],"word":[7,59],"segmentation,":[8],"POS":[9],"tagging":[10],"and":[11],"text":[12,25],"normalization.":[13],"Different":[14],"from":[15],"previous":[16],"methods,":[17],"the":[18,28,56,74],"can":[20,53],"be":[21],"trained":[22],"on":[23,44,61],"standard":[24],"corpora,":[26],"overcoming":[27],"lack":[29],"of":[30,58,70],"annotated":[31,41],"microblog":[32],"corpora.":[33],"To":[34],"evaluate":[35],"our":[36,50],"model,":[37],"we":[38],"develop":[39],"an":[40,64],"corpus":[42],"based":[43],"microblogs.":[45],"Experimental":[46],"results":[47],"show":[48],"that":[49],"help":[54],"improve":[55],"performance":[57],"segmentation":[60,68],"microblogs,":[62],"giving":[63],"error":[65],"reduction":[66],"in":[67],"accuracy":[69],"12.02%,":[71],"compared":[72],"to":[73],"traditional":[75],"approach.":[76]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}