{"id":"https://openalex.org/W400322755","doi":null,"title":"Text Harmonization Strategies for Phrase-Based Statistical Machine Translation","display_name":"Text Harmonization Strategies for Phrase-Based Statistical Machine Translation","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W400322755","mag":"400322755"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.359.8293","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.359.8293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://liu.diva-portal.org/smash/get/diva2:516686/FULLTEXT01/","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-76766","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051985869","display_name":"Sara Stymne","orcid":"https://orcid.org/0000-0003-3726-9399","observed_orcids":["https://orcid.org/0000-0003-3726-9399"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Sara Stymne","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5051985869"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.451,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82389873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"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/T10201","display_name":"Speech Recognition and Synthesis","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/phrase-based-machine-translation","display_name":"phrase-based statistical machine translation","score":1.0},{"id":"https://openalex.org/keywords/compounding","display_name":"compounding","score":0.7200000286102295},{"id":"https://openalex.org/keywords/definiteness","display_name":"definiteness","score":0.9419999718666077},{"id":"https://openalex.org/keywords/word-order","display_name":"word order","score":0.9819999933242798},{"id":"https://openalex.org/keywords/out-of-vocabulary-words","display_name":"out-of-vocabulary words","score":0.9390000104904175},{"id":"https://openalex.org/keywords/transformation-rules","display_name":"transformation rules","score":0.6449999809265137},{"id":"https://openalex.org/keywords/rule-based-transformation","display_name":"rule-based transformation","score":0.4580000042915344},{"id":"https://openalex.org/keywords/morphological-complexity","display_name":"morphological complexity","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.8353252410888672},{"id":"https://openalex.org/C2779962950","wikidata":"https://www.wikidata.org/wiki/Q5659376","display_name":"Harmonization","level":2,"score":0.7215263247489929},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7042455673217773},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6827272176742554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6303722858428955},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5830971598625183},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.5429574847221375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5343958735466003},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.4891541302204132},{"id":"https://openalex.org/C135784402","wikidata":"https://www.wikidata.org/wiki/Q6958279","display_name":"Evaluation of machine translation","level":5,"score":0.4668327867984772},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.43533599376678467},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14290514588356018},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.10371538996696472},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.051748126745224},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.359.8293","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.359.8293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://liu.diva-portal.org/smash/get/diva2:516686/FULLTEXT01/","raw_type":"text"},{"id":"pmh:oai:DiVA.org:liu-76766","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-76766","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"mag:400322755","doi":null,"is_oa":false,"landing_page_url":"http://liu.diva-portal.org/smash/get/diva2:516686/FULLTEXT01","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":{"id":"pmh:oai:DiVA.org:liu-76766","doi":null,"is_oa":true,"landing_page_url":"http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-76766","pdf_url":null,"source":{"id":"https://openalex.org/S4306401559","display_name":"KTH Publication Database DiVA (KTH Royal Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I86987016","host_organization_name":"KTH Royal Institute of Technology","host_organization_lineage":["https://openalex.org/I86987016"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":217,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W23077562","https://openalex.org/W35711202","https://openalex.org/W86336727","https://openalex.org/W121569490","https://openalex.org/W129135300","https://openalex.org/W158508907","https://openalex.org/W167345539","https://openalex.org/W179314280","https://openalex.org/W284974300","https://openalex.org/W294504433","https://openalex.org/W426788869","https://openalex.org/W429474256","https://openalex.org/W567326294","https://openalex.org/W580000981","https://openalex.org/W601321418","https://openalex.org/W623156858","https://openalex.org/W781672987","https://openalex.org/W1236045544","https://openalex.org/W1479669738","https://openalex.org/W1480857181","https://openalex.org/W1489181569","https://openalex.org/W1489525520","https://openalex.org/W1492906232","https://openalex.org/W1510290649","https://openalex.org/W1510632846","https://openalex.org/W1517947178","https://openalex.org/W1519942606","https://openalex.org/W1535206496","https://openalex.org/W1535549990","https://openalex.org/W1535937474","https://openalex.org/W1563861331","https://openalex.org/W1572797009","https://openalex.org/W1574901103","https://openalex.org/W1576427988","https://openalex.org/W1585544221","https://openalex.org/W1595595359","https://openalex.org/W1603508585","https://openalex.org/W1631260214","https://openalex.org/W1647671624","https://openalex.org/W1736600331","https://openalex.org/W1765954950","https://openalex.org/W1815552937","https://openalex.org/W1819520634","https://openalex.org/W1856482117","https://openalex.org/W1868901511","https://openalex.org/W1885135473","https://openalex.org/W1969974515","https://openalex.org/W1973923101","https://openalex.org/W1977887743","https://openalex.org/W1978161643","https://openalex.org/W1983969726","https://openalex.org/W1996041053","https://openalex.org/W1997420744","https://openalex.org/W1999777333","https://openalex.org/W2006969979","https://openalex.org/W2008961349","https://openalex.org/W2015350341","https://openalex.org/W2016522586","https://openalex.org/W2016718885","https://openalex.org/W2016856586","https://openalex.org/W2017802499","https://openalex.org/W2018616927","https://openalex.org/W2031196180","https://openalex.org/W2031912044","https://openalex.org/W2038698865","https://openalex.org/W2046224275","https://openalex.org/W2049633694","https://openalex.org/W2051991014","https://openalex.org/W2054533749","https://openalex.org/W2057900969","https://openalex.org/W2060127787","https://openalex.org/W2064656742","https://openalex.org/W2066792529","https://openalex.org/W2078745840","https://openalex.org/W2078861931","https://openalex.org/W2079629183","https://openalex.org/W2080012968","https://openalex.org/W2082571252","https://openalex.org/W2083155042","https://openalex.org/W2086757171","https://openalex.org/W2091542740","https://openalex.org/W2096842796","https://openalex.org/W2097997328","https://openalex.org/W2098439409","https://openalex.org/W2100794359","https://openalex.org/W2101105183","https://openalex.org/W2101200183","https://openalex.org/W2103866953","https://openalex.org/W2103890644","https://openalex.org/W2105245376","https://openalex.org/W2106818711","https://openalex.org/W2108460050","https://openalex.org/W2108540317","https://openalex.org/W2109871145","https://openalex.org/W2111798208","https://openalex.org/W2112900913","https://openalex.org/W2113538861","https://openalex.org/W2113641473","https://openalex.org/W2113788796","https://openalex.org/W2115081467","https://openalex.org/W2116599427","https://openalex.org/W2117504261","https://openalex.org/W2117642127","https://openalex.org/W2117745860","https://openalex.org/W2119825066","https://openalex.org/W2120349760","https://openalex.org/W2123301721","https://openalex.org/W2123551014","https://openalex.org/W2124769992","https://openalex.org/W2124807415","https://openalex.org/W2126013273","https://openalex.org/W2126241965","https://openalex.org/W2127589427","https://openalex.org/W2129158994","https://openalex.org/W2130784467","https://openalex.org/W2132248251","https://openalex.org/W2132446289","https://openalex.org/W2132891320","https://openalex.org/W2133263080","https://openalex.org/W2133512280","https://openalex.org/W2133651532","https://openalex.org/W2133665027","https://openalex.org/W2133888301","https://openalex.org/W2134285054","https://openalex.org/W2134800885","https://openalex.org/W2134913565","https://openalex.org/W2135002837","https://openalex.org/W2135161317","https://openalex.org/W2135399222","https://openalex.org/W2136094405","https://openalex.org/W2137220564","https://openalex.org/W2137387514","https://openalex.org/W2138477841","https://openalex.org/W2139770225","https://openalex.org/W2140826881","https://openalex.org/W2141182089","https://openalex.org/W2141725067","https://openalex.org/W2143134347","https://openalex.org/W2144385980","https://openalex.org/W2144600658","https://openalex.org/W2144879357","https://openalex.org/W2144900797","https://openalex.org/W2145685230","https://openalex.org/W2145956377","https://openalex.org/W2146574666","https://openalex.org/W2146685010","https://openalex.org/W2146867136","https://openalex.org/W2147192413","https://openalex.org/W2147925066","https://openalex.org/W2148381207","https://openalex.org/W2151738913","https://openalex.org/W2152263452","https://openalex.org/W2153653739","https://openalex.org/W2153800732","https://openalex.org/W2153903004","https://openalex.org/W2154124206","https://openalex.org/W2154849084","https://openalex.org/W2155539936","https://openalex.org/W2156556476","https://openalex.org/W2156985047","https://openalex.org/W2157435188","https://openalex.org/W2158195707","https://openalex.org/W2158388102","https://openalex.org/W2161227214","https://openalex.org/W2161792612","https://openalex.org/W2162245945","https://openalex.org/W2162346592","https://openalex.org/W2163353449","https://openalex.org/W2163582407","https://openalex.org/W2163942301","https://openalex.org/W2164394329","https://openalex.org/W2164766438","https://openalex.org/W2165828367","https://openalex.org/W2166306133","https://openalex.org/W2166418450","https://openalex.org/W2167393476","https://openalex.org/W2168966090","https://openalex.org/W2169279899","https://openalex.org/W2170464899","https://openalex.org/W2171034805","https://openalex.org/W2171421863","https://openalex.org/W2242975712","https://openalex.org/W2250307271","https://openalex.org/W2272090139","https://openalex.org/W2280403519","https://openalex.org/W2295893272","https://openalex.org/W2331822200","https://openalex.org/W2395243984","https://openalex.org/W2397601298","https://openalex.org/W2401082558","https://openalex.org/W2404928265","https://openalex.org/W2405635321","https://openalex.org/W2405762604","https://openalex.org/W2407523058","https://openalex.org/W2407799926","https://openalex.org/W2471470790","https://openalex.org/W2494948086","https://openalex.org/W2580381134","https://openalex.org/W2583532397","https://openalex.org/W2787701609","https://openalex.org/W2796493717","https://openalex.org/W2895810819","https://openalex.org/W2976428324","https://openalex.org/W3019633459","https://openalex.org/W3103098195","https://openalex.org/W3135790904","https://openalex.org/W3142580018","https://openalex.org/W3167119764","https://openalex.org/W3198021593","https://openalex.org/W3202110839","https://openalex.org/W3202354456","https://openalex.org/W3202429746","https://openalex.org/W3203149905","https://openalex.org/W3203439809","https://openalex.org/W3209717902","https://openalex.org/W7097452425"],"related_works":["https://openalex.org/W2153124406","https://openalex.org/W2418711689","https://openalex.org/W2800771610","https://openalex.org/W2100937742","https://openalex.org/W1586984800","https://openalex.org/W7071057273","https://openalex.org/W4322096478","https://openalex.org/W3161538114","https://openalex.org/W2359680434","https://openalex.org/W1996465127"],"abstract_inverted_index":{"In":[0],"this":[1,75,236],"thesis":[2],"I":[3,73,92,130,155,171,188,229,256,284,311],"aim":[4],"to":[5,57,70,100,143,160,206,250,277,343,354],"improve":[6,101,207,344],"phrase-based":[7,350],"statistical":[8,30,345],"machine":[9,140,346],"translation":[10,158,174,224,294,347],"(PBSMT)":[11],"in":[12,223,253,292],"a":[13,89,104,220,231,243,298],"number":[14],"of":[15,20,35,210,260,288,321],"ways":[16,287],"by":[17,28,80,132,164,183,318],"the":[18,49,64,117,121,144,150,157,161,208,293,319,349],"use":[19,320],"text":[21,78,95,327],"harmonization":[22,96,337],"strategies.":[23],"PBSMT":[24,90,102,308,317],"systems":[25],"are":[26,51,217,339],"built":[27],"training":[29,86,162],"models":[31],"on":[32,106,124],"large":[33,240],"corpora":[34],"human":[36],"translations.":[37],"This":[38],"architecture":[39],"generally":[40],"performs":[41],"well":[42],"for":[43,53,248,280,315,326],"languages":[44,50,176,227],"with":[45,55,103,168,177],"similar":[46,84],"structure.":[47],"If":[48],"different":[52],"example":[54],"respect":[56],"word":[58,111,265,271],"order":[59,209],"or":[60,139,146],"morphological":[61],"complexity,":[62],"however,":[63],"standard":[65],"methods":[66,276,334,338],"do":[67],"not":[68],"tend":[69],"work":[71],"well.":[72],"address":[74,131],"problem":[76,221,237],"through":[77],"harmonization,":[79,328],"making":[81],"texts":[82],"more":[83,355],"before":[85],"and":[87,113,185,198,228,238,264,267,323,329],"applying":[88,133],"system.":[91],"investigate":[93],"how":[94,200,249],"can":[97,180,203,303],"be":[98,181,204,278,304],"used":[99,205,279],"focus":[105,122],"four":[107],"areas:":[108],"compounding,":[109],"definiteness,":[110],"order,":[112],"unknown":[114,153,166,290],"words.":[115],"For":[116,149],"first":[118],"three":[119],"areas,":[120],"is":[123],"linguistic":[125],"differences":[126,252],"between":[127],"languages,":[128],"which":[129,273,302],"transformation":[134],"rules,":[135],"using":[136,268,306],"either":[137],"rule-based":[138],"learning-based":[141],"techniques,":[142],"source":[145],"target":[147],"data.":[148],"last":[151],"area,":[152],"words,":[154],"harmonize":[156],"input":[159],"data":[163],"replacing":[165,289],"words":[167,291],"known":[169],"alternatives.":[170],"show":[172,199,330],"that":[173,193,234,332],"into":[175,225],"closed":[178],"compounds":[179],"improved":[182],"splitting":[184],"merging":[186,191],"compounds.":[187],"develop":[189],"new":[190],"algorithms":[192,197],"outperform":[194],"previously":[195],"suggested":[196],"part-of-speech":[201],"tags":[202],"compound":[211],"parts.":[212],"Scandinavian":[213,226],"definite":[214],"noun":[215],"phrases":[216],"identified":[218],"as":[219],"forPBSMT":[222],"propose":[230,257],"preprocessing":[232],"approach":[233],"addresses":[235],"gives":[239],"improvements":[241],"over":[242],"baseline.":[244],"Several":[245],"previous":[246],"proposals":[247],"handle":[251],"reordering":[254,263],"exist;":[255],"two":[258],"types":[259],"extensions,":[261],"iterating":[262],"alignment":[266],"automatically":[269],"induced":[270],"classes,":[272],"allow":[274],"these":[275,333],"less-resourced":[281],"languages.":[282],"Finally":[283],"identify":[285],"several":[286,313],"input,":[295],"most":[296],"notably":[297],"spell":[299],"checking-inspired":[300],"algorithm,":[301],"trained":[305],"character-based":[307],"techniques.":[309],"Overall":[310],"present":[312],"approaches":[314],"extending":[316],"pre-":[322],"postprocessing":[324],"techniques":[325],"experimentally":[331],"work.":[335],"Text":[336],"an":[340],"efficient":[341],"way":[342],"within":[348],"approach,":[351],"without":[352],"resorting":[353],"complex":[356],"models.":[357]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}