{"id":"https://openalex.org/W2252059851","doi":"https://doi.org/10.3115/v1/w14-5301","title":"Corpus-based Study and Identification of Mandarin Chinese Light Verb Variations","display_name":"Corpus-based Study and Identification of Mandarin Chinese Light Verb Variations","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2252059851","doi":"https://doi.org/10.3115/v1/w14-5301","mag":"2252059851"},"language":"en","primary_location":{"id":"doi:10.3115/v1/w14-5301","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5301","pdf_url":"https://aclanthology.org/W14-5301.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/W14-5301.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024924150","display_name":"Chu\u2010Ren Huang","orcid":"https://orcid.org/0000-0002-8526-5520"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chu-Ren Huang","raw_affiliation_strings":["Department of CBS, The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CBS, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055029056","display_name":"Jingxia Lin","orcid":"https://orcid.org/0000-0001-9930-7368"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jingxia Lin","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080584027","display_name":"Menghan Jiang","orcid":"https://orcid.org/0000-0001-5005-147X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Menghan JIANG","raw_affiliation_strings":["Department of CBS, The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CBS, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100542973","display_name":"Hongzhi Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hongzhi Xu","raw_affiliation_strings":["Department of CBS, The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of CBS, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9865000247955322,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12353","display_name":"Lexicography and Language Studies","score":0.9797000288963318,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.9507088661193848},{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.6878657341003418},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6730947494506836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6520493030548096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5874021053314209},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5153912305831909},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4215548634529114},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39902788400650024},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.08368426561355591}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.9507088661193848},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.6878657341003418},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6730947494506836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6520493030548096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5874021053314209},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5153912305831909},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4215548634529114},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39902788400650024},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.08368426561355591},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3115/v1/w14-5301","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5301","pdf_url":"https://aclanthology.org/W14-5301.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.676.7936","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.676.7936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://anthology.aclweb.org/W/W14/W14-5301.pdf","raw_type":"text"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/58844","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/58844","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.3115/v1/w14-5301","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/w14-5301","pdf_url":"https://aclanthology.org/W14-5301.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 First Workshop on Applying NLP Tools to Similar Languages, Varieties and Dialects","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5899999737739563,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2252059851.pdf","grobid_xml":"https://content.openalex.org/works/W2252059851.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W86907710","https://openalex.org/W100638832","https://openalex.org/W1638801140","https://openalex.org/W2117909082","https://openalex.org/W2133990480","https://openalex.org/W2165173456","https://openalex.org/W2167850217","https://openalex.org/W2250373302","https://openalex.org/W2250453746","https://openalex.org/W2332964166","https://openalex.org/W2394579447","https://openalex.org/W2495083898","https://openalex.org/W3119782651","https://openalex.org/W3148310287","https://openalex.org/W6677535196"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2385333991","https://openalex.org/W2980645678","https://openalex.org/W1501055685","https://openalex.org/W1971037590","https://openalex.org/W2076300332","https://openalex.org/W841103693","https://openalex.org/W1537287363","https://openalex.org/W2020703271","https://openalex.org/W2369051942"],"abstract_inverted_index":{"When":[0],"PRC":[1],"was":[2,122,217,242],"founded":[3],"on":[4,42,141],"mainland":[5,18,83],"China":[6,19,56,84],"and":[7,20,76,82,147,150,181,226,275,291,306,311],"the":[8,15,36,66,96,131,153,184,202,258,266,289,292,297,301,312],"KMT":[9],"retreated":[10],"to":[11,46,57,59,70,99,179,201,235,244],"Taiwan":[12,21,51,81,148,307],"in":[13,55,145,193,207,209,263,304],"1949,":[14],"relation":[16],"between":[17,35,80],"became":[22],"a":[23,62,107,190,218,269,284],"classical":[24],"Cold":[25],"War":[26],"instance.":[27],"Neither":[28],"travel,":[29],"visit,":[30],"nor":[31],"correspondences":[32],"were":[33],"allowed":[34],"people":[37,52],"until":[38],"1987,":[39],"when":[40],"government":[41],"both":[43],"sides":[44],"started":[45],"allow":[47,95],"small":[48],"number":[49],"of":[50,88,117,134,156,186,204,268],"with":[53,229,296],"relatives":[54],"return":[58],"visit":[60],"through":[61],"third":[63],"location.":[64],"Although":[65],"thawing":[67],"eventually":[68],"lead":[69],"frequent":[71],"exchanges,":[72],"direct":[73],"travel":[74],"links,":[75],"close":[77],"commercial":[78],"ties":[79],"today,":[85],"38":[86],"years":[87],"total":[89],"isolation":[90],"from":[91,222],"each":[92,248],"other":[93],"did":[94],"language":[97],"use":[98],"develop":[100],"into":[101],"different":[102],"varieties,":[103],"which":[104],"have":[105,309],"become":[106],"popular":[108],"topic":[109,192],"for":[110,168,214,247,288],"mainly":[111],"lexical":[112],"studies":[113],"(e.g.,":[114],"Grammatical":[115],"difference":[116],"these":[118,157],"two":[119,158,169,259],"variants,":[120],"however,":[121],"not":[123],"well":[124],"studied":[125],"beyond":[126],"anecdotal":[127],"observation,":[128],"partly":[129],"because":[130],"near":[132],"identity":[133],"their":[135],"grammatical":[136],"systems.":[137],"This":[138],"paper":[139],"focuses":[140],"light":[142,154,187,205,236,249,302],"verb":[143,237,250],"variations":[144,290,310,313],"Mainland":[146,305],"variants":[149,159,260],"finds":[151],"that":[152,232,246],"verbs":[155,165,188,206,303],"indeed":[160,308],"show":[161,245,261],"distributional":[162],"tendencies.":[163],"Light":[164],"are":[166,173,294],"chosen":[167],"reasons:":[170],"first,":[171],"they":[172],"semantically":[174],"bleached":[175],"hence":[176],"more":[177],"susceptible":[178],"changes":[180],"variations.":[182,238],"Second,":[183],"classification":[185],"is":[189,252],"challenging":[191],"NLP.":[194],"We":[195],"hope":[196],"our":[197],"study":[198,203,216],"will":[199],"contribute":[200,234],"Chinese":[208,223],"general.":[210],"The":[211],"data":[212],"adopted":[213],"this":[215],"comparable":[219],"corpus":[220],"extracted":[221],"Gigaword":[224],"Corpus":[225],"manually":[227],"annotated":[228],"contextual":[230],"features":[231],"may":[233],"A":[239],"multivariate":[240,298],"analysis":[241,287],"conducted":[243],"there":[251],"at":[253],"least":[254],"one":[255],"context":[256],"where":[257],"differences":[262],"tendencies":[264],"(usually":[265],"presence/absence":[267],"tendency":[270],"rather":[271],"than":[272],"contrasting":[273],"tendencies)":[274],"can":[276,314],"be":[277,315],"differentiated.":[278,317],"In":[279],"addition,":[280],"we":[281],"carried":[282],"out":[283],"K-Means":[285],"clustering":[286],"results":[293],"consistent":[295],"analysis,":[299],"i.e.":[300],"successfully":[316]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}