{"id":"https://openalex.org/W137929102","doi":null,"title":"Improving chinese-english machine translation through better source-side linguistic processing","display_name":"Improving chinese-english machine translation through better source-side linguistic processing","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W137929102","mag":"137929102"},"language":"en","primary_location":{"id":"mag:137929102","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=1835208","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","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/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"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056695196","display_name":"Pi-Chuan Chang","orcid":"https://orcid.org/0000-0003-3021-6446","observed_orcids":["https://orcid.org/0000-0003-3021-6446"]},"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":"Pi-Chuan Chang","raw_affiliation_strings":["Stanford University"],"raw_orcid":"https://orcid.org/0000-0003-3021-6446","affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.02031056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"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":0.9990000128746033,"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":0.9990000128746033,"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":0.00019999999494757503,"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/T10759","display_name":"Translation Studies and Practices","score":0.00019999999494757503,"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/chinese-english-machine-translation","display_name":"Chinese-English machine translation","score":0.9700000286102295},{"id":"https://openalex.org/keywords/chinese-word-segmentation","display_name":"Chinese word segmentation","score":0.9670000076293945},{"id":"https://openalex.org/keywords/word-order","display_name":"word order","score":0.492000013589859},{"id":"https://openalex.org/keywords/phrase-based-machine-translation","display_name":"phrase-based statistical machine translation","score":0.7120000123977661},{"id":"https://openalex.org/keywords/relative-clauses","display_name":"relative clauses","score":0.48100000619888306},{"id":"https://openalex.org/keywords/prepositional-phrases","display_name":"prepositional phrases","score":0.7940000295639038},{"id":"https://openalex.org/keywords/error-analysis","display_name":"error analysis","score":0.46700000762939453}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820969223976135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.710507869720459},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.6351422071456909},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5957946181297302},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5760306119918823},{"id":"https://openalex.org/C70777604","wikidata":"https://www.wikidata.org/wiki/Q257885","display_name":"Word order","level":2,"score":0.4891364872455597},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.48499390482902527},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4777195453643799},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4606042504310608},{"id":"https://openalex.org/C153962237","wikidata":"https://www.wikidata.org/wiki/Q1401131","display_name":"Noun phrase","level":3,"score":0.41694340109825134},{"id":"https://openalex.org/C121934690","wikidata":"https://www.wikidata.org/wiki/Q1084","display_name":"Noun","level":2,"score":0.3692353367805481},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:137929102","doi":null,"is_oa":false,"landing_page_url":"https://dl.acm.org/citation.cfm?id=1835208","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W12923685","https://openalex.org/W23077562","https://openalex.org/W25062297","https://openalex.org/W44506435","https://openalex.org/W82340936","https://openalex.org/W97972967","https://openalex.org/W149848483","https://openalex.org/W201231365","https://openalex.org/W786936280","https://openalex.org/W1508977358","https://openalex.org/W1510052640","https://openalex.org/W1517947178","https://openalex.org/W1551202288","https://openalex.org/W1575907248","https://openalex.org/W1588242179","https://openalex.org/W1969974515","https://openalex.org/W1979145089","https://openalex.org/W2001064229","https://openalex.org/W2006969979","https://openalex.org/W2016856586","https://openalex.org/W2032772856","https://openalex.org/W2033295622","https://openalex.org/W2035807240","https://openalex.org/W2036516910","https://openalex.org/W2038881539","https://openalex.org/W2048808408","https://openalex.org/W2056469463","https://openalex.org/W2069598966","https://openalex.org/W2086202918","https://openalex.org/W2086825453","https://openalex.org/W2096765155","https://openalex.org/W2098594428","https://openalex.org/W2098875891","https://openalex.org/W2101105183","https://openalex.org/W2102301788","https://openalex.org/W2108301419","https://openalex.org/W2108460050","https://openalex.org/W2109494378","https://openalex.org/W2117642127","https://openalex.org/W2118563017","https://openalex.org/W2122609803","https://openalex.org/W2126241965","https://openalex.org/W2131988669","https://openalex.org/W2135161317","https://openalex.org/W2136925175","https://openalex.org/W2140016149","https://openalex.org/W2143263475","https://openalex.org/W2144091461","https://openalex.org/W2144279206","https://openalex.org/W2146113428","https://openalex.org/W2146574666","https://openalex.org/W2146798791","https://openalex.org/W2147302173","https://openalex.org/W2147880316","https://openalex.org/W2152263452","https://openalex.org/W2153653739","https://openalex.org/W2153800732","https://openalex.org/W2154124206","https://openalex.org/W2156985047","https://openalex.org/W2157435188","https://openalex.org/W2158065314","https://openalex.org/W2161227214","https://openalex.org/W2162245945","https://openalex.org/W2164766438","https://openalex.org/W2166905217","https://openalex.org/W2169724380","https://openalex.org/W2171421863","https://openalex.org/W2242975712","https://openalex.org/W2252066972","https://openalex.org/W2406273306","https://openalex.org/W2437005631","https://openalex.org/W2467575451","https://openalex.org/W2787109023"],"related_works":["https://openalex.org/W7098835976","https://openalex.org/W2358724409","https://openalex.org/W2139227106","https://openalex.org/W936351679","https://openalex.org/W2131988669","https://openalex.org/W2021856631","https://openalex.org/W61894391","https://openalex.org/W2376336214","https://openalex.org/W7096817680","https://openalex.org/W2095907708"],"abstract_inverted_index":{"Machine":[0],"Translation":[1],"(MT)":[2],"is":[3,43,66,98,136],"a":[4,20,64,70,105,246,299,332,367],"task":[5],"with":[6,76,121],"multiple":[7],"components,":[8],"each":[9],"of":[10,63,217,249,288],"which":[11,295],"can":[12,117,222,312,351],"be":[13,223,313,370],"very":[14,82],"challenging.":[15],"This":[16],"thesis":[17,40],"focuses":[18,41],"on":[19,27,42,84,149,239],"difficult":[21],"language":[22],"pair\u2014Chinese":[23],"to":[24,100,107,154,171,178,264,279,302,317,328,334,360,372],"English\u2014and":[25],"works":[26],"several":[28],"language-specific":[29],"aspects":[30],"that":[31,80,115,253],"make":[32,352],"translation":[33,168,347],"more":[34,255,358],"difficult.":[35],"\r\nThe":[36,131],"first":[37,145],"challenge":[38,133],"this":[39,242,341],"the":[44,47,61,85,109,122,157,271,286,289,345,353],"differences":[45],"in":[46,112,210,308,337],"writing":[48],"systems.":[49,182,232],"In":[50,241],"Chinese":[51,73,94,113,141,196,250,267,292,338,354],"there":[52],"are":[53,199,262],"no":[54],"explicit":[55],"boundaries":[56],"between":[57,140,259],"words,":[58],"and":[59,103,126,142,197,227,278,310,362],"even":[60],"definition":[62],"word":[74,95,124,138,165,184,208,220,293,355],"unclear.":[67],"We":[68,144,330],"build":[69],"general":[71],"purpose":[72],"segmenter":[75,96],"linguistically":[77],"inspired":[78],"features":[79],"performs":[81],"well":[83],"SIGHAN":[86],"2005":[87],"bakeoff":[88],"data.":[89],"Then":[90],"we":[91,134,174,244,284,343,350,363],"study":[92,285],"how":[93,163],"performance":[97],"related":[99],"MT":[101,129,152,181,231,276],"performance,":[102],"provide":[104],"way":[106],"tune":[108],"unit":[111],"so":[114],"it":[116],"better":[118],"match":[119],"up":[120],"English":[123,198,346],"granularity,":[125],"therefore":[127,311],"improve":[128,179,280,344],"performance.":[130,282],"second":[132],"address":[135],"different":[137,164,207,219,306,373],"order":[139],"English.":[143,303,318,329],"perform":[146],"error":[147],"analysis":[148],"three":[150],"state-of-the-art":[151,274],"systems":[153],"see":[155],"what":[156],"most":[158,272,290],"prominent":[159],"problems":[160],"are,":[161],"especially":[162,186],"orders":[166,209,221,356],"cause":[167,228,322],"errors.":[169,193],"According":[170],"our":[172],"findings,":[173],"propose":[175,331],"two":[176],"solutions":[177],"Chinese-to-English":[180],"\r\nFirst,":[183],"reordering,":[185],"over":[187],"longer":[188,323],"distances,":[189],"has":[190],"caused":[191],"many":[192,236],"Even":[194],"though":[195],"both":[200],"Subject-Verb-Object":[201],"(SVO)":[202],"languages,":[203],"they":[204],"usually":[205],"use":[206],"noun":[211],"phrases,":[212,214],"prepositional":[213,378],"etc.":[215],"Many":[216],"these":[218,266],"long":[224],"distance":[225,324],"ones":[226],"difficulty":[229],"for":[230],"There":[233],"have":[234,298],"been":[235],"previous":[237],"studies":[238],"this.":[240],"thesis,":[243],"introduce":[245],"richer":[247],"set":[248],"grammatical":[251,268],"relations":[252,258,269],"describes":[254],"semantically":[256],"abstract":[257],"words.":[260],"\r\nWe":[261],"able":[263],"integrate":[265],"into":[270],"used,":[273],"phrase-based":[275],"system":[277],"its":[281],"\r\nSecond,":[283],"behavior":[287],"common":[291],"(DE),":[294],"does":[296],"not":[297],"direct":[300],"mapping":[301],"DE":[304,368],"serves":[305],"functions":[307],"Chinese,":[309],"ambiguous":[314],"when":[315,326,366],"translating":[316,327],"It":[319],"might":[320],"also":[321,364],"reordering":[325],"classifier":[333],"disambiguate":[335,365],"DEs":[336],"text.":[339],"Using":[340],"classifier,":[342],"quality":[348],"because":[349],"much":[357],"similar":[359],"English,":[361],"should":[369],"translated":[371],"constructions":[374],"(e.g.,":[375],"relative":[376],"clause,":[377],"phrase,":[379],"etc.).":[380]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2016-06-24T00:00:00"}