{"id":"https://openalex.org/W2094597777","doi":"https://doi.org/10.1145/1034780.1034786","title":"A maximum-entropy chinese parser augmented by transformation-based learning","display_name":"A maximum-entropy chinese parser augmented by transformation-based learning","publication_year":2004,"publication_date":"2004-06-01","ids":{"openalex":"https://openalex.org/W2094597777","doi":"https://doi.org/10.1145/1034780.1034786","mag":"2094597777"},"language":"en","primary_location":{"id":"doi:10.1145/1034780.1034786","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1034780.1034786","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5065856469","display_name":"Pascale Fung","orcid":"https://orcid.org/0000-0002-0628-7132"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Pascale Fung","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong","Hong Kong University of Science and Technology; Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology; Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051682329","display_name":"Grace Ngai","orcid":"https://orcid.org/0000-0002-2027-168X"},"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":"Grace Ngai","raw_affiliation_strings":["Hong Kong Polytechnic University, Hong Kong","#N##TAB##TAB##TAB##TAB# Hong Kong Polytechnic University, Hong Kong#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Hong Kong Polytechnic University, Hong Kong#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102161530","display_name":"Yang Yongsheng","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yongsheng Yang","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong","Hong Kong University of Science and Technology; Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology; Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033822869","display_name":"Benfeng Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Benfeng Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong","Hong Kong University of Science and Technology; Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology; Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.1219,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.93958972,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"3","issue":"2","first_page":"159","last_page":"168"},"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":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9805999994277954,"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":0.8873039484024048},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.8026605248451233},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.7892311811447144},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7616720199584961},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.688859760761261},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.6006521582603455},{"id":"https://openalex.org/keywords/parser-combinator","display_name":"Parser combinator","score":0.5220713019371033},{"id":"https://openalex.org/keywords/top-down-parsing","display_name":"Top-down parsing","score":0.4626826345920563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8873039484024048},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.8026605248451233},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7892311811447144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7616720199584961},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.688859760761261},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6006521582603455},{"id":"https://openalex.org/C118364021","wikidata":"https://www.wikidata.org/wiki/Q7139956","display_name":"Parser combinator","level":3,"score":0.5220713019371033},{"id":"https://openalex.org/C42560504","wikidata":"https://www.wikidata.org/wiki/Q15419395","display_name":"Top-down parsing","level":3,"score":0.4626826345920563}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1034780.1034786","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1034780.1034786","pdf_url":null,"source":{"id":"https://openalex.org/S56575750","display_name":"ACM Transactions on Asian Language Information Processing","issn_l":"1530-0226","issn":["1530-0226","1558-3430"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Asian Language Information Processing","raw_type":"journal-article"},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/10256","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/10256","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":"Journal/Magazine Article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-21214","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-10044253419&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W82889912","https://openalex.org/W1507894573","https://openalex.org/W1558333962","https://openalex.org/W1623072288","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W2000566875","https://openalex.org/W2031164055","https://openalex.org/W2045628429","https://openalex.org/W2117400858","https://openalex.org/W2145216370","https://openalex.org/W2146113428","https://openalex.org/W2158873310","https://openalex.org/W2217873082","https://openalex.org/W2990644213","https://openalex.org/W6658244484","https://openalex.org/W6770616414"],"related_works":["https://openalex.org/W1585034923","https://openalex.org/W2106048106","https://openalex.org/W28706907","https://openalex.org/W3151198705","https://openalex.org/W2281562628","https://openalex.org/W2559370752","https://openalex.org/W2817971408","https://openalex.org/W4226372027","https://openalex.org/W2167662847","https://openalex.org/W2094597777"],"abstract_inverted_index":{"Parsing,":[0],"the":[1,18,79,100,107,113,121,137,143,158,165,186,204,220,225,246],"task":[2],"of":[3,17,65,78,88,98,112,123,139],"identifying":[4],"syntactic":[5],"components,":[6],"e.g.,":[7],"noun":[8],"and":[9,35],"verb":[10],"phrases,":[11],"in":[12,21,62,70,91,106,151,157,162],"a":[13,48,89,92,96,104,130,140,191,214,240],"sentence,":[14],"is":[15,183,190,194],"one":[16],"fundamental":[19],"tasks":[20],"natural":[22,26],"language":[23,27,80,94,131],"processing.":[24],"Many":[25],"applications":[28],"such":[29],"as":[30,47,129,161],"spoken-language":[31],"understanding,":[32],"machine":[33],"translation,":[34],"information":[36],"extraction,":[37],"would":[38],"benefit":[39],"from,":[40],"or":[41],"even":[42],"require,":[43],"high":[44],"accuracy":[45],"parsing":[46,61],"preprocessing":[49],"step.":[50],"Even":[51],"though":[52],"most":[53,64,144,197],"state-of-the-art":[54],"statistical":[55,101,141,176,216],"parsers":[56,124],"were":[57],"initially":[58],"constructed":[59],"for":[60,125,136],"English,":[63],"them":[66],"are":[67,82,154,260],"not":[68,74,155],"language-specific,":[69],"that":[71,81,168,193,203,242,252,254,259],"they":[72],"do":[73],"rely":[75],"on":[76,224],"properties":[77],"specific":[83],"to":[84,170,181,184,262],"English.":[85],"Therefore,":[86],"construction":[87,122],"parser":[90,235,241,256],"given":[93],"becomes":[95],"matter":[97],"retraining":[99],"parameters":[102],"with":[103,236],"Treebank":[105],"corresponding":[108],"language.":[109],"The":[110],"development":[111,138],"Chinese":[114,128,153,182,199,226],"treebank":[115,227],"[Xia":[116],"et":[117],"al.":[118],"2000]":[119],"spurred":[120],"Chinese.":[126],"However,":[127],"poses":[132],"some":[133],"unique":[134],"problems":[135],"parser,":[142,217],"apparent":[145],"being":[146],"word":[147,187,267],"segmentation.":[148],"Since":[149],"words":[150],"written":[152],"delimited":[156],"same":[159],"way":[160],"Western":[163],"languages,":[164],"first":[166],"problem":[167],"needs":[169],"be":[171,179],"solved":[172],"before":[173],"an":[174,231],"existing":[175,232],"method":[177],"can":[178,243],"applied":[180],"identify":[185],"boundaries.":[188],"This":[189,211],"step":[192],"neglected":[195],"by":[196],"pre-existing":[198],"parsers,":[200],"which":[201,218],"assume":[202],"input":[205],"data":[206],"has":[207],"already":[208],"been":[209],"pre-segmented.":[210],"article":[212],"describes":[213],"character-based":[215],"gives":[219],"best":[221],"performance":[222],"to-date":[223],"data.":[228],"We":[229,249],"augment":[230],"maximum":[233],"entropy":[234],"transformation-based":[237],"learning,":[238],"creating":[239],"operate":[244],"at":[245],"character":[247],"level.":[248],"present":[250],"experiments":[251],"show":[253],"our":[255],"achieves":[257],"results":[258],"close":[261],"those":[263],"achievable":[264],"under":[265],"perfect":[266],"segmentation":[268],"conditions.":[269]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}