{"id":"https://openalex.org/W170557285","doi":null,"title":"Phrase Alignment Models for Statistical Machine Translation","display_name":"Phrase Alignment Models for Statistical Machine Translation","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W170557285","mag":"170557285"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org/ark:/13030/qt6md7793w","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/6md7793w","pdf_url":"https://escholarship.org/uc/item/6md7793w","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/uc/item/6md7793w","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072072153","display_name":"John DeNero","orcid":"https://orcid.org/0000-0001-9152-3891","observed_orcids":["https://orcid.org/0000-0001-9152-3891"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"John DeNero","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0001-9152-3891","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5072072153"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":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/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"}},{"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"}}],"keywords":[{"id":"https://openalex.org/keywords/phrase-alignment","display_name":"phrase alignment","score":0.9430000185966492},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.9850000143051147},{"id":"https://openalex.org/keywords/parallel-corpora","display_name":"parallel corpus","score":0.7419999837875366},{"id":"https://openalex.org/keywords/phrase-segmentation","display_name":"phrase segmentation","score":0.48899999260902405},{"id":"https://openalex.org/keywords/alignment-model","display_name":"alignment model","score":0.47099998593330383},{"id":"https://openalex.org/keywords/word-alignment","display_name":"word alignment","score":0.46700000762939453},{"id":"https://openalex.org/keywords/sentence-alignment","display_name":"sentence alignment","score":0.3700000047683716},{"id":"https://openalex.org/keywords/discriminative-models","display_name":"discriminative models","score":0.44200000166893005},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.8769999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8225645422935486},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7198030948638916},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7008202075958252},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.6859260201454163},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6133466958999634},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6006619930267334},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44953423738479614},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.4433615207672119},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43298518657684326},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"pmh:oai:escholarship.org/ark:/13030/qt6md7793w","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/6md7793w","pdf_url":"https://escholarship.org/uc/item/6md7793w","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},{"id":"pmh:qt6md7793w","doi":null,"is_oa":true,"landing_page_url":"http://www.escholarship.org/uc/item/6md7793w","pdf_url":"http://www.escholarship.org/uc/item/6md7793w","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"DeNero, John Sturdy. (2010). Phrase Alignment Models for Statistical Machine Translation. UC Berkeley: Electrical Engineering & Computer Sciences. Retrieved from: http://www.escholarship.org/uc/item/6md7793w","raw_type":"dissertation"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.460.9149","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.460.9149","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.eecs.berkeley.edu/~denero/research/denero_phd_thesis.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.638.4377","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.638.4377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.denero.org/content/pubs/denero_thesis.pdf","raw_type":"text"},{"id":"pmh:oai:berkeley.edu:28722-bk0007q6z62","doi":null,"is_oa":false,"landing_page_url":"http://techreports.lib.berkeley.edu/accessPages/EECS-2010-161.html","pdf_url":null,"source":{"id":"https://openalex.org/S7407050879","display_name":"UC Berkeley","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I95457486","host_organization_name":"University of California, Berkeley","host_organization_lineage":["https://openalex.org/I95457486"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"technical reports"},{"id":"mag:170557285","doi":null,"is_oa":false,"landing_page_url":"https://escholarship.org/content/qt6md7793w/qt6md7793w.pdf","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:escholarship.org/ark:/13030/qt6md7793w","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/6md7793w","pdf_url":"https://escholarship.org/uc/item/6md7793w","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"etd"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W170557285.pdf","grobid_xml":"https://content.openalex.org/works/W170557285.grobid-xml"},"referenced_works_count":79,"referenced_works":["https://openalex.org/W91928571","https://openalex.org/W263845233","https://openalex.org/W1496659931","https://openalex.org/W1517947178","https://openalex.org/W1606508130","https://openalex.org/W1631260214","https://openalex.org/W1714704734","https://openalex.org/W1965420956","https://openalex.org/W1989584251","https://openalex.org/W1997420744","https://openalex.org/W2006912660","https://openalex.org/W2006969979","https://openalex.org/W2038698865","https://openalex.org/W2069429561","https://openalex.org/W2100682730","https://openalex.org/W2101105183","https://openalex.org/W2101656755","https://openalex.org/W2108452152","https://openalex.org/W2109664771","https://openalex.org/W2111142112","https://openalex.org/W2111568643","https://openalex.org/W2115526192","https://openalex.org/W2116211107","https://openalex.org/W2116410915","https://openalex.org/W2117126688","https://openalex.org/W2117840636","https://openalex.org/W2118439278","https://openalex.org/W2119168550","https://openalex.org/W2119224513","https://openalex.org/W2119314391","https://openalex.org/W2119388680","https://openalex.org/W2122228338","https://openalex.org/W2122244345","https://openalex.org/W2124807415","https://openalex.org/W2124810114","https://openalex.org/W2126270798","https://openalex.org/W2126377586","https://openalex.org/W2126946601","https://openalex.org/W2129083353","https://openalex.org/W2130195263","https://openalex.org/W2130959832","https://openalex.org/W2133137812","https://openalex.org/W2133229022","https://openalex.org/W2133512280","https://openalex.org/W2134729743","https://openalex.org/W2136657878","https://openalex.org/W2136925175","https://openalex.org/W2137592969","https://openalex.org/W2138165032","https://openalex.org/W2138414624","https://openalex.org/W2138753018","https://openalex.org/W2139175732","https://openalex.org/W2140702357","https://openalex.org/W2143230354","https://openalex.org/W2144169942","https://openalex.org/W2145473818","https://openalex.org/W2146574666","https://openalex.org/W2147706904","https://openalex.org/W2147880316","https://openalex.org/W2148675933","https://openalex.org/W2152213375","https://openalex.org/W2153653739","https://openalex.org/W2154099718","https://openalex.org/W2156985047","https://openalex.org/W2157052604","https://openalex.org/W2157381218","https://openalex.org/W2157512532","https://openalex.org/W2158266063","https://openalex.org/W2158388102","https://openalex.org/W2160245618","https://openalex.org/W2161227214","https://openalex.org/W2161792612","https://openalex.org/W2164151151","https://openalex.org/W2164454850","https://openalex.org/W2164732909","https://openalex.org/W2169724380","https://openalex.org/W2169755331","https://openalex.org/W2437005631","https://openalex.org/W3161877658"],"related_works":["https://openalex.org/W2215355985","https://openalex.org/W2010532441","https://openalex.org/W2548768491","https://openalex.org/W2070974859","https://openalex.org/W1493039547","https://openalex.org/W7010511357","https://openalex.org/W7099779971","https://openalex.org/W2150903784","https://openalex.org/W4232765812","https://openalex.org/W3008208031"],"abstract_inverted_index":{"The":[0,144,278],"goal":[1],"of":[2,64,77,87,118,133,147,159,220,224,275,281,320],"a":[3,12,124,137,225,325,354],"machine":[4,365],"translation":[5,366],"(MT)":[6],"system":[7],"is":[8,150,284,342],"to":[9,121,151,165,171,179,210,232,266,272,285,295,305,344],"automatically":[10,242],"translate":[11,111,166],"document":[13,26,114,139],"written":[14,27],"in":[15,28,37,44,58,99,123,140,188,238,334,350,361,368],"some":[16],"human":[17],"input":[18,102,113],"language":[19,31],"(e.g.,":[20,32],"Mandarin":[21],"Chinese)":[22],"into":[23,136,155,256,312],"an":[24,29,112,141],"equivalent":[25],"output":[30,104,142],"English).":[33],"This":[34,214,263,340],"task---so":[35],"simple":[36],"its":[38,45,119],"specification,":[39],"and":[40,95,103,127,168,205,258,315,337],"yet":[41],"so":[42,206],"rich":[43],"complexities---has":[46],"challenged":[47],"computer":[48],"science":[49],"researchers":[50],"for":[51],"60":[52],"years.":[53],"While":[54],"MT":[55,78,109],"systems":[56,79,110,367],"are":[57,169,175,247,303],"wide":[59],"use":[60,369],"today,":[61],"the":[62,75,101,131,191,291,345,347],"problem":[63,358],"producing":[65],"human-quality":[66],"translations":[67,132,154,219,245,269],"remains":[68],"unsolved.":[69],"Statistical":[70],"approaches":[71],"have":[72,90],"substantially":[73],"improved":[74],"quality":[76],"by":[80,93,115,252],"effectively":[81],"exploiting":[82],"parallel":[83,125],"corpora:":[84],"large":[85,239],"collections":[86],"documents":[88],"that":[89,161,228,246,359],"been":[91],"translated":[92,186,198],"people,":[94],"therefore":[96],"naturally":[97],"occur":[98],"both":[100,335],"languages.":[105,262],"Broadly":[106],"characterized,":[107],"statistical":[108,273,307,364],"matching":[116],"fragments":[117,135,158],"contents":[120],"examples":[122],"corpus,":[126],"then":[128],"stitching":[129],"together":[130],"those":[134],"coherent":[138,317],"language.":[143],"central":[145],"challenge":[146],"this":[148,282,351],"approach":[149,265,294],"distill":[152],"example":[153],"reusable":[156],"parts:":[157],"sentences":[160,195,251],"we":[162],"know":[163],"how":[164],"robustly":[167],"likely":[170],"recur.":[172],"Individual":[173],"words":[174,227],"certainly":[176],"common":[177],"enough":[178,230],"recur,":[180],"but":[181,202,235],"they":[182],"often":[183],"cannot":[184,207],"be":[185,197,208,233],"correctly":[187],"isolation.":[189],"At":[190],"other":[192],"extreme,":[193],"whole":[194],"can":[196],"without":[199],"much":[200],"context,":[201],"rarely":[203],"repeat,":[204],"recycled":[209],"build":[211],"new":[212],"translations.":[213,298],"thesis":[215,283,352],"focuses":[216],"on":[217],"acquiring":[218,267,296],"phrases:":[221],"contiguous":[222],"sequences":[223],"few":[226],"encapsulate":[229],"context":[231],"translatable,":[234],"recur":[236],"frequently":[237],"corpora.":[240],"We":[241],"identify":[243],"phrase-level":[244],"contained":[248],"within":[249],"human-translated":[250],"partitioning":[253],"each":[254],"sentence":[255,322],"phrases":[257,260],"aligning":[259],"across":[261],"alignment-based":[264],"phrasal":[268,297,318],"gives":[270],"rise":[271],"models":[274,302,329,333,348],"phrase":[276,288,300,327],"alignment.":[277],"cumulative":[279],"result":[280,341],"establish":[286],"model-based":[287],"alignment":[289,301,313,328,357],"as":[290],"most":[292],"effective":[293],"Only":[299],"able":[304],"incorporate":[306],"signals":[308],"about":[309],"multi-word":[310],"constructions":[311],"decisions":[314],"score":[316],"analyses":[319],"full":[321],"pairs.":[323],"As":[324],"result,":[326],"outperform":[330],"classical":[331],"word-level":[332],"generative":[336],"discriminative":[338],"settings.":[339],"fundamental":[343],"field:":[346],"proposed":[349],"address":[353],"general,":[355],"language-independent":[356],"arises":[360],"all":[362],"state-of-the-art":[363],"today.":[370]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-09-04T10:56:28.161419","created_date":"2016-06-24T00:00:00"}