{"id":"https://openalex.org/W2155677886","doi":null,"title":"Resourcing machine translation with parallel treebanks","display_name":"Resourcing machine translation with parallel treebanks","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2155677886","mag":"2155677886"},"language":"en","primary_location":{"id":"pmh:oai:doras.dcu.ie:15071","doi":null,"is_oa":false,"landing_page_url":"https://doras.dcu.ie/15071/1/JohnThesis.pdf","pdf_url":"https://doras.dcu.ie/15071/1/JohnThesis.pdf","source":{"id":"https://openalex.org/S4306401511","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doras.dcu.ie/15071/1/JohnThesis.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024248692","display_name":"John F. Tinsley","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"John Tinsley","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5024248692"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0,"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/T12031","display_name":"Speech and dialogue systems","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.7139999866485596},{"id":"https://openalex.org/keywords/parallel-treebanks","display_name":"parallel treebanks","score":0.9779999852180481},{"id":"https://openalex.org/keywords/syntax-based-machine-translation","display_name":"syntax-based machine translation","score":0.890999972820282},{"id":"https://openalex.org/keywords/phrase-structure-trees","display_name":"phrase structure trees","score":0.7670000195503235},{"id":"https://openalex.org/keywords/phrase-based-machine-translation","display_name":"phrase-based statistical machine translation","score":0.8299999833106995},{"id":"https://openalex.org/keywords/phrase-tables","display_name":"phrase tables","score":0.8180000185966492},{"id":"https://openalex.org/keywords/synchronous-grammars","display_name":"synchronous grammars","score":0.9399999976158142},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.6990000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8619520664215088},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.7460600137710571},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7398617267608643},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7010353207588196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6908501982688904},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.6442347168922424},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6393975019454956},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.46081656217575073},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.34473615884780884}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:doras.dcu.ie:15071","doi":null,"is_oa":false,"landing_page_url":"https://doras.dcu.ie/15071/1/JohnThesis.pdf","pdf_url":"https://doras.dcu.ie/15071/1/JohnThesis.pdf","source":{"id":"https://openalex.org/S4306401511","display_name":"Dublin City University Open Access Institutional Repository (Dublin City University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I42934936","host_organization_name":"Dublin City University","host_organization_lineage":["https://openalex.org/I42934936"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"pmh:http://www.rian.ie/40443/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/15071/","pdf_url":"https://doras.dcu.ie/15071/1/JohnThesis.pdf","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin 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/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tinsley, John (2010) Resourcing machine translation with parallel treebanks. PhD thesis, Dublin City University.","raw_type":"Other"},{"id":"mag:2155677886","doi":null,"is_oa":false,"landing_page_url":"http://doras.dcu.ie/15071/","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:http://www.rian.ie/40443/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/15071/","pdf_url":"https://doras.dcu.ie/15071/1/JohnThesis.pdf","source":{"id":"https://openalex.org/S4306400033","display_name":"Arrow@dit (Dublin 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/I4210144925","host_organization_name":"Technological University Dublin","host_organization_lineage":["https://openalex.org/I4210144925"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tinsley, John (2010) Resourcing machine translation with parallel treebanks. PhD thesis, Dublin City University.","raw_type":"Other"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2155677886.pdf","grobid_xml":"https://content.openalex.org/works/W2155677886.grobid-xml"},"referenced_works_count":122,"referenced_works":["https://openalex.org/W7519655","https://openalex.org/W9638488","https://openalex.org/W19756977","https://openalex.org/W22168010","https://openalex.org/W23077562","https://openalex.org/W83938146","https://openalex.org/W96030503","https://openalex.org/W108437174","https://openalex.org/W132913264","https://openalex.org/W135639250","https://openalex.org/W181173957","https://openalex.org/W206967138","https://openalex.org/W222053410","https://openalex.org/W350356983","https://openalex.org/W1483201900","https://openalex.org/W1489525520","https://openalex.org/W1492045078","https://openalex.org/W1498040058","https://openalex.org/W1500096219","https://openalex.org/W1503402034","https://openalex.org/W1517947178","https://openalex.org/W1521937871","https://openalex.org/W1523418713","https://openalex.org/W1551202288","https://openalex.org/W1555286493","https://openalex.org/W1555786581","https://openalex.org/W1557279510","https://openalex.org/W1568694948","https://openalex.org/W1568793342","https://openalex.org/W1574901103","https://openalex.org/W1580700384","https://openalex.org/W1586104099","https://openalex.org/W1608909294","https://openalex.org/W1631260214","https://openalex.org/W1672171594","https://openalex.org/W1676720115","https://openalex.org/W1865928303","https://openalex.org/W1916559533","https://openalex.org/W1934041838","https://openalex.org/W1938853666","https://openalex.org/W1965116319","https://openalex.org/W1972913706","https://openalex.org/W1974815860","https://openalex.org/W1982725271","https://openalex.org/W1986569439","https://openalex.org/W1992254746","https://openalex.org/W2000394794","https://openalex.org/W2006969979","https://openalex.org/W2008959343","https://openalex.org/W2012681659","https://openalex.org/W2031351647","https://openalex.org/W2049633694","https://openalex.org/W2051840895","https://openalex.org/W2058335193","https://openalex.org/W2071606701","https://openalex.org/W2073955506","https://openalex.org/W2078861931","https://openalex.org/W2081580037","https://openalex.org/W2084500805","https://openalex.org/W2091721240","https://openalex.org/W2093647425","https://openalex.org/W2097333193","https://openalex.org/W2098051944","https://openalex.org/W2098162425","https://openalex.org/W2101105183","https://openalex.org/W2103015765","https://openalex.org/W2107895803","https://openalex.org/W2108540317","https://openalex.org/W2112900913","https://openalex.org/W2113788796","https://openalex.org/W2115081467","https://openalex.org/W2116316001","https://openalex.org/W2119168550","https://openalex.org/W2121404172","https://openalex.org/W2122974883","https://openalex.org/W2123301721","https://openalex.org/W2124164392","https://openalex.org/W2124807415","https://openalex.org/W2125474347","https://openalex.org/W2126033735","https://openalex.org/W2126102937","https://openalex.org/W2131933497","https://openalex.org/W2132622673","https://openalex.org/W2133229022","https://openalex.org/W2133512280","https://openalex.org/W2135345769","https://openalex.org/W2136477195","https://openalex.org/W2136612048","https://openalex.org/W2139123334","https://openalex.org/W2139403546","https://openalex.org/W2139456735","https://openalex.org/W2140343992","https://openalex.org/W2141852716","https://openalex.org/W2143008661","https://openalex.org/W2146574666","https://openalex.org/W2148407683","https://openalex.org/W2150087485","https://openalex.org/W2150378737","https://openalex.org/W2150903784","https://openalex.org/W2152263452","https://openalex.org/W2153653739","https://openalex.org/W2154124206","https://openalex.org/W2154563865","https://openalex.org/W2156945896","https://openalex.org/W2156985047","https://openalex.org/W2158195707","https://openalex.org/W2158388102","https://openalex.org/W2159316909","https://openalex.org/W2160266640","https://openalex.org/W2161742089","https://openalex.org/W2161792612","https://openalex.org/W2162245945","https://openalex.org/W2165666205","https://openalex.org/W2168966090","https://openalex.org/W2169599995","https://openalex.org/W2236481623","https://openalex.org/W2258247613","https://openalex.org/W2405762604","https://openalex.org/W2437005631","https://openalex.org/W2592190371","https://openalex.org/W2794298879","https://openalex.org/W3043064541"],"related_works":["https://openalex.org/W2084500805","https://openalex.org/W2166485291","https://openalex.org/W38602834","https://openalex.org/W2131933497","https://openalex.org/W7095879187","https://openalex.org/W1562934833","https://openalex.org/W3036630479","https://openalex.org/W1676720115","https://openalex.org/W7095475961","https://openalex.org/W7099349673"],"abstract_inverted_index":{"The":[0],"benefits":[1],"of":[2,18,57,67,77,95,111,117,135,152,161,169,219,230,235,255,290,302,320],"syntax-based":[3,99,206,330],"approaches":[4],"to":[5,29,92,179,213],"data-driven":[6],"machine":[7,145],"translation":[8,34,265,321,326],"(MT)":[9],"are":[10,140,177,201],"clear:":[11],"given":[12],"the":[13,41,65,75,93,109,132,159,211,245,249,318],"right":[14],"model,":[15],"a":[16,90,103,126,150,170,180,227,233,282,288,329],"combination":[17],"hierarchical":[19],"structure,":[20],"constituent":[21],"labels":[22],"and":[23,189,238],"morphological":[24],"information":[25,246],"can":[26,267,295,316],"be":[27,214,268,297],"exploited":[28,215],"produce":[30],"more":[31],"fluent,":[32],"grammatical":[33],"output.":[35],"This":[36,121],"has":[37],"been":[38],"demonstrated":[39],"by":[40,101,167,270],"recent":[42],"shift":[43],"in":[44,64,190,205,216,241,252,264,293,308],"research":[45],"focus":[46],"towards":[47],"such":[48,58],"linguistically":[49,276],"motivated":[50,277],"approaches.":[51],"However,":[52],"one":[53],"issue":[54],"facing":[55],"developers":[56],"models":[59],"that":[60,197,262,287],"is":[61,74],"not":[62,142,202],"encountered":[63],"development":[66],"state-of-the-art":[68],"string-based":[69],"statistical":[70,257],"MT":[71,100,192,258,331],"(SMT)":[72],"systems":[73],"lack":[76],"available":[78],"syntactically":[79],"annotated":[80,182],"training":[81],"data":[82,236],"for":[83,98,108,131,144],"many":[84],"languages.\\n\\nIn":[85],"this":[86,222],"thesis,":[87],"we":[88,195,224,243,305],"propose":[89],"solution":[91],"problem":[94],"limited":[96],"resources":[97],"introducing":[102],"novel":[104],"sub-sentential":[105],"alignment":[106],"algorithm":[107],"induction":[110],"translational":[112],"equivalence":[113],"links":[114],"between":[115],"pairs":[116,279],"phrase":[118,273,278],"structure":[119],"trees.":[120],"algorithm,":[122],"which":[123,139,175,242,309],"operates":[124],"on":[125,324],"language":[127,154,239],"pair-independent":[128],"basis,":[129],"allows":[130],"automatic":[133],"generation":[134],"large-scale":[136],"parallel":[137,165,185,199,250,283,314],"treebanks":[138,166,200,251,315],"useful":[141,204],"only":[143,203],"translation,":[146],"but":[147,208],"also":[148,209,296],"across":[149,232],"variety":[151,234],"natural":[153],"processing":[155],"tasks.":[156],"We":[157,260],"demonstrate":[158,261],"viability":[160],"our":[162],"automatically":[163],"generated":[164],"means":[168],"thorough":[171],"evaluation":[172],"process":[173],"during":[174],"they":[176],"compared":[178],"manually":[181],"gold":[183],"standard":[184],"treebank":[186],"both":[187],"intrinsically":[188],"an":[191],"task.\\n\\nFollowing":[193],"this,":[194],"hypothesise":[196],"these":[198],"MT,":[207],"have":[210],"potential":[212],"other":[217,291],"paradigms":[218],"MT.":[220],"To":[221],"end,":[223],"carry":[225],"out":[226],"large":[228],"number":[229,289],"experiments":[231],"sets":[237],"pairs,":[240],"exploit":[244],"encoded":[247],"within":[248],"various":[253],"components":[254],"phrase-based":[256],"systems.":[259],"improvements":[263],"accuracy":[266],"achieved":[269],"enhancing":[271],"SMT":[272,294],"tables":[274],"with":[275,299],"extracted":[280,312],"from":[281,313,328],"treebank,":[284],"while":[285],"showing":[286],"features":[292],"supplemented":[298],"varying":[300],"degrees":[301],"effectiveness.":[303],"Finally,":[304],"examine":[306],"ways":[307],"synchronous":[310],"grammars":[311],"improve":[317],"quality":[319],"output,":[322],"focussing":[323],"real":[325],"examples":[327],"system.":[332]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}
