{"id":"https://openalex.org/W634920035","doi":null,"title":"Phrase extraction and rescoring in statistical machine translation","display_name":"Phrase extraction and rescoring in statistical machine translation","publication_year":2014,"publication_date":"2014-11-01","ids":{"openalex":"https://openalex.org/W634920035","mag":"634920035"},"language":"en","primary_location":{"id":"pmh:http://www.rian.ie/104877/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/19971/","pdf_url":"http://doras.dcu.ie/19971/","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Srivastava, Ankit Kumar (2014) Phrase extraction and rescoring in statistical machine translation. PhD thesis, Dublin City University.","raw_type":"Other"},"volume":null,"type":"other","is_traditional":false,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://doras.dcu.ie/19971/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104168278","display_name":"Ankit Kumar Srivastava","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ankit Kumar Srivastava","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5104168278"],"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":0.9994999766349792,"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":0.9994999766349792,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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-based-machine-translation","display_name":"phrase-based statistical machine translation","score":0.9660000205039978},{"id":"https://openalex.org/keywords/phrase-extraction","display_name":"phrase extraction","score":0.8659999966621399},{"id":"https://openalex.org/keywords/rescoring","display_name":"rescoring","score":0.7020000219345093},{"id":"https://openalex.org/keywords/re-ranking","display_name":"re-ranking","score":0.9390000104904175},{"id":"https://openalex.org/keywords/n-best-lists","display_name":"N-best lists","score":0.6859999895095825},{"id":"https://openalex.org/keywords/decoding-errors","display_name":"decoding errors","score":0.5540000200271606},{"id":"https://openalex.org/keywords/parallel-treebanks","display_name":"parallel treebanks","score":0.7820000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295720815658569},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.7844250202178955},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.7076332569122314},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6675378680229187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6536422371864319},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.5425591468811035},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5190718770027161},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4798957109451294},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.43279391527175903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3264591097831726},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20099273324012756},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13679486513137817},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:http://www.rian.ie/104877/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/19971/","pdf_url":"http://doras.dcu.ie/19971/","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Srivastava, Ankit Kumar (2014) Phrase extraction and rescoring in statistical machine translation. PhD thesis, Dublin City University.","raw_type":"Other"},{"id":"pmh:oai:doras.dcu.ie:19971","doi":null,"is_oa":true,"landing_page_url":"https://doras.dcu.ie/19971/1/AnkitKSPhDThesis.pdf","pdf_url":"http://doras.dcu.ie/19971/1/AnkitKSPhDThesis.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Thesis"},{"id":"mag:634920035","doi":null,"is_oa":false,"landing_page_url":"http://doras.dcu.ie/19971/1/AnkitKSPhDThesis.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:http://www.rian.ie/104877/","doi":null,"is_oa":true,"landing_page_url":"http://doras.dcu.ie/19971/","pdf_url":"http://doras.dcu.ie/19971/","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Srivastava, Ankit Kumar (2014) Phrase extraction and rescoring in statistical machine translation. PhD thesis, Dublin City University.","raw_type":"Other"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4290828396","display_name":"CSET CNGL: Next Generation Localisation (CNGL)","funder_award_id":"07/CE/I1142","funder_id":"https://openalex.org/F4320320847","funder_display_name":"Science Foundation Ireland"}],"funders":[{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W634920035.pdf","grobid_xml":"https://content.openalex.org/works/W634920035.grobid-xml"},"referenced_works_count":78,"referenced_works":["https://openalex.org/W19756977","https://openalex.org/W22168010","https://openalex.org/W23077562","https://openalex.org/W31462306","https://openalex.org/W34679601","https://openalex.org/W222053410","https://openalex.org/W585912846","https://openalex.org/W635530177","https://openalex.org/W1489525520","https://openalex.org/W1489834179","https://openalex.org/W1492045078","https://openalex.org/W1517377188","https://openalex.org/W1521937871","https://openalex.org/W1529616844","https://openalex.org/W1536179742","https://openalex.org/W1555286493","https://openalex.org/W1631260214","https://openalex.org/W1632114991","https://openalex.org/W1773803948","https://openalex.org/W1916559533","https://openalex.org/W1934041838","https://openalex.org/W1984566630","https://openalex.org/W1986543644","https://openalex.org/W1992097457","https://openalex.org/W2006969979","https://openalex.org/W2013086054","https://openalex.org/W2031351647","https://openalex.org/W2034991102","https://openalex.org/W2062766658","https://openalex.org/W2082421078","https://openalex.org/W2095755718","https://openalex.org/W2096389047","https://openalex.org/W2097333193","https://openalex.org/W2098051944","https://openalex.org/W2101105183","https://openalex.org/W2108892043","https://openalex.org/W2111335636","https://openalex.org/W2115548327","https://openalex.org/W2118960083","https://openalex.org/W2121404172","https://openalex.org/W2123301721","https://openalex.org/W2124807415","https://openalex.org/W2128878305","https://openalex.org/W2129785447","https://openalex.org/W2131933497","https://openalex.org/W2132873493","https://openalex.org/W2139621418","https://openalex.org/W2142112143","https://openalex.org/W2143564602","https://openalex.org/W2146574666","https://openalex.org/W2149327368","https://openalex.org/W2152263452","https://openalex.org/W2153439141","https://openalex.org/W2153653739","https://openalex.org/W2153800732","https://openalex.org/W2154124206","https://openalex.org/W2154757770","https://openalex.org/W2155677886","https://openalex.org/W2156985047","https://openalex.org/W2158195707","https://openalex.org/W2160266640","https://openalex.org/W2160571323","https://openalex.org/W2161792612","https://openalex.org/W2162842776","https://openalex.org/W2165666205","https://openalex.org/W2166905217","https://openalex.org/W2167393476","https://openalex.org/W2170852307","https://openalex.org/W2183711971","https://openalex.org/W2236481623","https://openalex.org/W2437005631","https://openalex.org/W2463396630","https://openalex.org/W2502023533","https://openalex.org/W2592190371","https://openalex.org/W2790246984","https://openalex.org/W2915991136","https://openalex.org/W2917029047","https://openalex.org/W3196862065"],"related_works":["https://openalex.org/W2766244031","https://openalex.org/W1542743110","https://openalex.org/W39836547","https://openalex.org/W2183711971","https://openalex.org/W2398262598","https://openalex.org/W2153124406","https://openalex.org/W2121351739","https://openalex.org/W2285400755","https://openalex.org/W2113199498","https://openalex.org/W2418711689"],"abstract_inverted_index":{"The":[0],"lack":[1],"of":[2,21,95,138,162,182,196,213,220,233,274,292],"linguistically":[3,96,293],"motivated":[4,97,294],"translation":[5,126,135,147,154,186,192,221],"units":[6],"or":[7,193],"phrase":[8,37,55,78,98,286,295],"pairs":[9,38],"in":[10,83,200,235],"Phrase-based":[11],"Statistical":[12],"Machine":[13],"Translation":[14],"(PB-SMT)":[15],"systems":[16],"is":[17,29,86,109,149],"a":[18,62,75,139,144,190,197,206,247],"well-known":[19],"source":[20,66],"error.":[22],"One":[23],"approach":[24,245],"to":[25,30,103,115,143,169,189,228,246],"minimise":[26,229],"such":[27],"errors":[28,173],"supplement":[31],"the":[32,53,81,92,106,123,133,151,159,180,201,211,218,230,236,252,279],"standard":[33],"PB-SMT":[34,107,140,176,198,207,280],"models":[35],"with":[36,58,255,283],"extracted":[39],"from":[40],"parallel":[41],"treebanks":[42],"(linguistically":[43],"annotated":[44],"and":[45,68,167,223,265],"aligned":[46],"corpora).":[47],"In":[48,158],"this":[49,163],"thesis,":[50,164],"we":[51,165,240],"extend":[52,241],"treebank-based":[54,285],"extraction":[56,79],"framework":[57,249],"percolated":[59],"dependencies":[60],"\u2013":[61,67],"hitherto":[63],"unutilised":[64],"knowledge":[65],"evaluate":[69],"its":[70],"usability":[71],"through":[72],"more":[73],"than":[74],"dozen":[76],"syntax-aware":[77],"models.\\nHowever,":[80],"improvement":[82],"system":[84,281],"performance":[85,290],"neither":[87],"consistent":[88],"nor":[89],"conclusive":[90],"despite":[91],"proven":[93],"advantages":[94],"pairs.":[99,296],"This":[100],"leads":[101],"us":[102],"hypothesize":[104],"that":[105],"pipeline":[108],"flawed":[110],"as":[111],"it":[112,155],"often":[113],"fails":[114],"access":[116],"perfectly":[117],"good":[118],"phrase-pairs":[119],"while":[120],"searching":[121],"for":[122],"highest":[124],"scoring":[125],"(decoding).":[127],"A":[128],"model":[129,148,172],"error":[130],"occurs":[131],"when":[132],"highest-probability":[134],"(actual":[136],"output":[137,195,222],"system)":[141,199],"according":[142],"statistical":[145],"machine":[146],"not":[150],"most":[152,187],"accurate":[153],"can":[156,277],"produce.":[157],"second":[160],"part":[161],"identify":[166],"attempt":[168],"trace":[170],"these":[171],"across":[174],"state-of-the-art":[175],"decoders":[177],"by":[178,205,250,267],"locating":[179],"position":[181],"oracle":[183],"translations":[184],"(the":[185],"similar":[188],"reference":[191],"expected":[194],"n-best":[202,237,253,275],"lists":[203,254,276],"generated":[204],"decoder.":[208],"We":[209,259],"analyse":[210],"impact":[212],"individual":[214],"decoding":[215],"features":[216],"on":[217,269],"quality":[219],"introduce":[224],"two":[225],"rescoring":[226,244,251,273],"algorithms":[227],"lower":[231],"ranking":[232],"oracles":[234],"lists.":[238],"Finally,":[239],"our":[242,271],"oracle-based":[243,272],"reranking":[248,257],"additional":[256],"features.":[258],"observe":[260],"limited":[261],"but":[262],"optimistic":[263],"success":[264],"conclude":[266],"speculating":[268],"how":[270],"help":[278],"(supplemented":[282],"multiple":[284],"extractions)":[287],"get":[288],"optimal":[289],"out":[291]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2016-06-24T00:00:00"}