{"id":"https://openalex.org/W1584847608","doi":null,"title":"An incremental syntactic language model for statistical phrase-based machine translation","display_name":"An incremental syntactic language model for statistical phrase-based machine translation","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W1584847608","mag":"1584847608"},"language":"en","primary_location":{"id":"mag:1584847608","doi":null,"is_oa":false,"landing_page_url":"https://conservancy.umn.edu/handle/11299/121791","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":"dissertation","is_traditional":true,"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/A5086362177","display_name":"William Schuler","orcid":"https://orcid.org/0000-0002-8780-2174","observed_orcids":["https://orcid.org/0000-0002-8780-2174"]},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"William Schuler","raw_affiliation_strings":["University of\u00a0Minnesota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of\u00a0Minnesota","institution_ids":["https://openalex.org/I130238516"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006314068","display_name":"Lane Schwartz","orcid":"https://orcid.org/0000-0003-2609-8133","observed_orcids":["https://orcid.org/0000-0003-2609-8133"]},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lane Schwartz","raw_affiliation_strings":["University of\u00a0Minnesota"],"raw_orcid":"https://orcid.org/0000-0003-2609-8133","affiliations":[{"raw_affiliation_string":"University of\u00a0Minnesota","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130238516"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.9980000257492065,"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":0.9980000257492065,"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":0.0013000000035390258,"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":0.00019999999494757503,"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/hierarchical-hidden-markov-models","display_name":"hierarchical hidden Markov models","score":0.9409999847412109},{"id":"https://openalex.org/keywords/phrase-based-machine-translation","display_name":"phrase-based statistical machine translation","score":0.8769999742507935},{"id":"https://openalex.org/keywords/statistical-machine-translation","display_name":"statistical machine translation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/perplexity-reduction","display_name":"perplexity reduction","score":0.7250000238418579},{"id":"https://openalex.org/keywords/out-of-domain-generalization","display_name":"out-of-domain generalization","score":0.6600000262260437},{"id":"https://openalex.org/keywords/language-model-interpolation","display_name":"language model interpolation","score":0.8180000185966492},{"id":"https://openalex.org/keywords/urdu-english-translation","display_name":"Urdu-English translation","score":0.7860000133514404},{"id":"https://openalex.org/keywords/n-gram-language-models","display_name":"n-gram language models","score":0.8379999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8518626689910889},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.7445237636566162},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7399448156356812},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.734468936920166},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7050751447677612},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5538453459739685},{"id":"https://openalex.org/C148526163","wikidata":"https://www.wikidata.org/wiki/Q6723733","display_name":"Machine translation software usability","level":4,"score":0.49654704332351685},{"id":"https://openalex.org/C24687705","wikidata":"https://www.wikidata.org/wiki/Q3753284","display_name":"Example-based machine translation","level":3,"score":0.48569902777671814},{"id":"https://openalex.org/C53893814","wikidata":"https://www.wikidata.org/wiki/Q7378909","display_name":"Rule-based machine translation","level":2,"score":0.47430136799812317},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.4570094048976898},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.4442235827445984},{"id":"https://openalex.org/C51802942","wikidata":"https://www.wikidata.org/wiki/Q7662211","display_name":"Synchronous context-free grammar","level":4,"score":0.4293099641799927},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.36454954743385315}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:1584847608","doi":null,"is_oa":false,"landing_page_url":"https://conservancy.umn.edu/handle/11299/121791","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":164,"referenced_works":["https://openalex.org/W23077562","https://openalex.org/W24102868","https://openalex.org/W76590478","https://openalex.org/W83938146","https://openalex.org/W100054011","https://openalex.org/W128136426","https://openalex.org/W214537020","https://openalex.org/W608050949","https://openalex.org/W1479669738","https://openalex.org/W1489525520","https://openalex.org/W1495432905","https://openalex.org/W1498232863","https://openalex.org/W1498238796","https://openalex.org/W1510052640","https://openalex.org/W1516146643","https://openalex.org/W1517947178","https://openalex.org/W1525810353","https://openalex.org/W1528941926","https://openalex.org/W1535015163","https://openalex.org/W1545286665","https://openalex.org/W1550038920","https://openalex.org/W1557279510","https://openalex.org/W1567277581","https://openalex.org/W1581810776","https://openalex.org/W1597533204","https://openalex.org/W1606076566","https://openalex.org/W1608789752","https://openalex.org/W1632114991","https://openalex.org/W1636244751","https://openalex.org/W1678112959","https://openalex.org/W1838574496","https://openalex.org/W1916559533","https://openalex.org/W1934041838","https://openalex.org/W1942952754","https://openalex.org/W1966812932","https://openalex.org/W1967689119","https://openalex.org/W1969483458","https://openalex.org/W1970961429","https://openalex.org/W1979495315","https://openalex.org/W1984314602","https://openalex.org/W1989705153","https://openalex.org/W1991133427","https://openalex.org/W1995875735","https://openalex.org/W1998802536","https://openalex.org/W2014034914","https://openalex.org/W2020477116","https://openalex.org/W2020755048","https://openalex.org/W2027077493","https://openalex.org/W2029825515","https://openalex.org/W2035227369","https://openalex.org/W2037894654","https://openalex.org/W2038248725","https://openalex.org/W2048390999","https://openalex.org/W2052047296","https://openalex.org/W2055522652","https://openalex.org/W2057492554","https://openalex.org/W2059800182","https://openalex.org/W2061910127","https://openalex.org/W2071277483","https://openalex.org/W2072875864","https://openalex.org/W2074729706","https://openalex.org/W2076749875","https://openalex.org/W2079145130","https://openalex.org/W2079323932","https://openalex.org/W2086324220","https://openalex.org/W2096175520","https://openalex.org/W2096253869","https://openalex.org/W2096894677","https://openalex.org/W2097033888","https://openalex.org/W2097790277","https://openalex.org/W2098188795","https://openalex.org/W2100281225","https://openalex.org/W2101105183","https://openalex.org/W2101656755","https://openalex.org/W2101752047","https://openalex.org/W2102872690","https://openalex.org/W2106477919","https://openalex.org/W2107990107","https://openalex.org/W2108082276","https://openalex.org/W2108540317","https://openalex.org/W2109664771","https://openalex.org/W2110020502","https://openalex.org/W2110104386","https://openalex.org/W2111142112","https://openalex.org/W2113788796","https://openalex.org/W2113998052","https://openalex.org/W2114434620","https://openalex.org/W2115081467","https://openalex.org/W2115289978","https://openalex.org/W2115321439","https://openalex.org/W2116316001","https://openalex.org/W2116957398","https://openalex.org/W2118686841","https://openalex.org/W2121380975","https://openalex.org/W2123301721","https://openalex.org/W2123893795","https://openalex.org/W2124807415","https://openalex.org/W2124861326","https://openalex.org/W2125259358","https://openalex.org/W2125474347","https://openalex.org/W2127191681","https://openalex.org/W2128201184","https://openalex.org/W2130903547","https://openalex.org/W2131933497","https://openalex.org/W2132382844","https://openalex.org/W2132622673","https://openalex.org/W2132634974","https://openalex.org/W2134237567","https://openalex.org/W2134634502","https://openalex.org/W2135831627","https://openalex.org/W2137227862","https://openalex.org/W2137268927","https://openalex.org/W2138203921","https://openalex.org/W2139424692","https://openalex.org/W2139895384","https://openalex.org/W2140343992","https://openalex.org/W2142632103","https://openalex.org/W2143008661","https://openalex.org/W2143075689","https://openalex.org/W2144002870","https://openalex.org/W2144600658","https://openalex.org/W2146143523","https://openalex.org/W2146192908","https://openalex.org/W2146574666","https://openalex.org/W2147192413","https://openalex.org/W2149327368","https://openalex.org/W2150378737","https://openalex.org/W2150615035","https://openalex.org/W2152263452","https://openalex.org/W2152907450","https://openalex.org/W2153439141","https://openalex.org/W2153653739","https://openalex.org/W2156094048","https://openalex.org/W2158388102","https://openalex.org/W2158707515","https://openalex.org/W2159080219","https://openalex.org/W2162346592","https://openalex.org/W2165003622","https://openalex.org/W2165257487","https://openalex.org/W2165666205","https://openalex.org/W2166667242","https://openalex.org/W2166905217","https://openalex.org/W2168966090","https://openalex.org/W2169279899","https://openalex.org/W2169362686","https://openalex.org/W2169528473","https://openalex.org/W2169599995","https://openalex.org/W2173749579","https://openalex.org/W2188741930","https://openalex.org/W2294868251","https://openalex.org/W2341171179","https://openalex.org/W2396581421","https://openalex.org/W2437005631","https://openalex.org/W2498472800","https://openalex.org/W2540531245","https://openalex.org/W2626190081","https://openalex.org/W2727254520","https://openalex.org/W2759423924","https://openalex.org/W2895810819","https://openalex.org/W2913887346","https://openalex.org/W3021713638","https://openalex.org/W3083113686","https://openalex.org/W3202429746","https://openalex.org/W4235553626"],"related_works":["https://openalex.org/W2096253869","https://openalex.org/W7066664789","https://openalex.org/W2152263452","https://openalex.org/W6987569351","https://openalex.org/W2001282348","https://openalex.org/W1822873414","https://openalex.org/W2158917268","https://openalex.org/W2188741930","https://openalex.org/W2386888287","https://openalex.org/W7071722359"],"abstract_inverted_index":{"Modern":[0],"machine":[1,76,184,472],"translation":[2,8,44,55,77,89,230,473,489,498,517],"techniques":[3],"typically":[4],"incorporate":[5],"both":[6,268],"a":[7,21,36,59,67,103,113,127,164,170,227,279,319,357,364,390,416,429,450,468,471,486],"model,":[9],"which":[10,25,500],"guides":[11],"how":[12,121],"individual":[13],"words":[14,30],"and":[15,20,31,119,149,172,262,270,428,491],"phrases":[16,32],"can":[17],"be":[18],"translated,":[19],"language":[22,68,110,137,165,180,192,214,219,244,260,265,282,292,297,366,387,394,413,441,444,509,523],"model":[23,69,111,123,138,181,193,215,245,266,283,293,298,367,388,395,414,445,453,510],"(LM),":[24],"promotes":[26],"fluency":[27],"as":[28,66,98,112,163,289,467],"translated":[29,37],"are":[33,97],"combined":[34],"into":[35,54,182,194],"sentence.":[38],"Most":[39],"attempts":[40],"to":[41,326,409,423,436,514],"inform":[42],"the":[43,71,84,155,161,196,234,286,295,307,311,327,349,370,398,410,424,437,455,503,516],"process":[45],"with":[46,310,389,446,464],"linguistic":[47],"knowledge":[48,65],"have":[49],"focused":[50],"on":[51,226,267,285,348,369,485],"infusing":[52],"syntax":[53],"models.":[56],"We":[57,101,153,168,186,201,251,303,481],"present":[58,102,154,202,223,252,482],"novel":[60,171],"technique":[61],"for":[62,175,211],"incorporating":[63,176],"syntactic":[64,109,136,191,213,238,264,291,296,312,340,354,386,425,508],"in":[70,142,209,299,315,323,361,397,406,420,433,477],"context":[72],"of":[73,83,94,106,130,160,236,243,257,301,454,470,497,505],"statistical":[74],"phrase-based":[75,183,198],"(Koehn":[78],"et":[79],"al.,":[80],"2003),":[81],"one":[82],"most":[85],"widely":[86],"used":[87,141],"modern":[88],"paradigms.":[90],"\r\nThe":[91],"major":[92],"contributions":[93],"this":[95,122,375],"work":[96,144],"follows:":[99],"*":[100,133,167,200],"formal":[104],"definition":[105,159],"an":[107,275,332,462,493],"incremental":[108,179,190,507],"Hierarchical":[114],"Hidden":[115],"Markov":[116],"Model":[117],"(HHMM),":[118],"detail":[120],"is":[124,247,449,458,511],"estimated":[125],"from":[126],"treebank":[128],"corpus":[129],"labelled":[131],"data.":[132,352,373],"The":[134,353],"HHMM":[135,162,189],"has":[139],"been":[140],"prior":[143],"involving":[145],"parsing,":[146],"speech":[147],"recognition,":[148],"semantic":[150],"role":[151],"labelling.":[152],"first":[156],"complete":[157],"algorithmic":[158],"model.":[166,442],"develop":[169],"general":[173],"method":[174],"any":[177],"generative":[178],"translation.":[185],"integrate":[187],"our":[188,212,237,263,290,339,385,506],"Moses,":[195],"prevailing":[197],"decoder.":[199],"empirical":[203,224,253,483],"results":[204,225,254,314,396,484,499],"that":[205,232,305,338,383,460,502],"demonstrate":[206,233],"substantial":[207],"improvements":[208],"perplexity":[210,256,317,324,362,401,407,421,434,448,466],"over":[216,363],"traditional":[217,280],"n-gram":[218,259],"models;":[220],"we":[221,336,380],"also":[222],"constrained":[228,487],"Urdu-English":[229,488],"task":[231,490],"use":[235,504],"LM.":[239],"\r\nA":[240,443],"standard":[241],"measure":[242],"quality":[246],"average":[248],"per-word":[249],"perplexity.":[250,302],"evaluating":[255],"various":[258],"models":[261],"in-domain":[269,276],"out-of-domain":[271,333,377],"test":[272,277,334,378],"sets.":[273],"On":[274,374],"set,":[278,335,379],"5-gram":[281,308,328,365,393,412,440],"trained":[284,347,368],"same":[287,350,371,376],"data":[288],"outperforms":[294,343],"terms":[300],"find":[304,337],"interpolating":[306,384],"LM":[309,313,329,341,355,426,463],"improved":[316],"results,":[318],"10%":[320],"absolute":[321,359,404,418,431],"reduction":[322,360,405,419,432],"compared":[325,408,422,435],"alone.":[330],"\r\nOn":[331],"substantially":[342],"all":[344],"other":[345],"LMs":[346],"training":[351,372],"demonstrates":[356],"58%":[358],"further":[381],"show":[382],"large":[391],"Gigaword-scale":[392,411],"best":[399],"overall":[400],"results\u2014a":[402],"61%":[403],"alone,":[415,427],"76%":[417],"90%":[430],"original":[438],"smaller":[439],"low":[447,465],"theoretically":[451],"good":[452],"language;":[456],"it":[457],"expected":[459],"using":[461],"component":[469],"system":[474],"should":[475],"result":[476],"more":[478,520],"fluent":[479,521],"translations.":[480,524],"perform":[492],"informal":[494],"manual":[495],"evaluation":[496],"suggests":[501],"indeed":[512],"serving":[513],"guide":[515],"algorithm":[518],"towards":[519],"target":[522]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2016-06-24T00:00:00"}