PHRASE AND NGRAM-BASED STATISTICAL MACHINE TRANSLATION SYSTEM COMBINATION
Multiples translations can be computed by one machine translation (MT) system or by different MT systems. We may assume that different MT systems make different errors due to using different models, generation strategies, or tweaks. An investigated technique, inherited from automatic speech recognit...
Saved in:
Published in | Applied artificial intelligence Vol. 23; no. 7; pp. 694 - 711 |
---|---|
Main Authors | , |
Format | Journal Article |
Language | English |
Published |
Philadelphia
Taylor & Francis Group
31.07.2009
Taylor & Francis Ltd |
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Multiples translations can be computed by one machine translation (MT) system or by different MT systems. We may assume that different MT systems make different errors due to using different models, generation strategies, or tweaks. An investigated technique, inherited from automatic speech recognition (ASR), is the so-called system combination that is based on combining the outputs of multiples MT systems. We combine the outputs of a phrase- and Ngram-based Statistical MT (SMT) systems using statistical criteria and additional rescoring features. |
---|---|
AbstractList | Multiples translations can be computed by one machine translation (MT) system or by different MT systems. We may assume that different MT systems make different errors due to using different models, generation strategies, or tweaks. An investigated technique, inherited from automatic speech recognition (ASR), is the so-called system combination that is based on combining the outputs of multiples MT systems. We combine the outputs of a phrase- and Ngram-based Statistical MT (SMT) systems using statistical criteria and additional rescoring features. Multiples translations can be computed by one machine translation (MT) system or by different MT systems. We may assume that different MT systems make different errors due to using different models, generation strategies, or tweaks. An investigated technique, inherited from automatic speech recognition (ASR), is the so-called system combination that is based on combining the outputs of multiples MT systems. We combine the outputs of a phrase- and Ngram-based Statistical MT (SMT) systems using statistical criteria and additional rescoring features. [PUBLICATION ABSTRACT] |
Author | Costa-Jussà, Marta R. Fonollosa, José A. R. |
Author_xml | – sequence: 1 givenname: Marta R. surname: Costa-Jussà fullname: Costa-Jussà, Marta R. email: marta.ruiz@barcelonamedia.org organization: Universitat Politècnica de Catalunya – sequence: 2 givenname: José A. R. surname: Fonollosa fullname: Fonollosa, José A. R. organization: Universitat Politècnica de Catalunya |
BookMark | eNqFkE9PwkAQxTcGEwH9AN4aD96qs7v9t4mXAhWa0GJoPXjaLO02gZQWd0uUb-8iniTG02Tmvd-byQxQr2kbidAthgcMATxCEFDmYmBACfgBgwvUN4Jve67j9lD_qNvG4FyhgdYbAMC-j_sofpktwyyywnRipdNlmNgj006sLA_zOMvjcTi3knA8i9PIypdhms3NfJFa2VuWR4k1XiSjOP0eXaPLStRa3vzUIXp9jvLxzJ4vpscYu6CMdba5UVTUY0AYW_m-UzK3dIA5VDDpQbAKjFoV4BSslKUnC4esCpdiJgmpfEGADtH9KXen2ve91B3frnUh61o0st1rTl3AxDGBQ3T3y7hp96oxt3GC3cDDxD2m4ZOpUK3WSlZ8p9ZboQ4cAz9-lp991jD-iVk3Vau24qNVdck7cahbVSnRFGt9TvHuszPk078k_XvxF4-piis |
Cites_doi | 10.1093/comjnl/7.4.308 10.1162/089120103321337421 10.1162/coli.2006.32.4.527 |
ContentType | Journal Article |
Copyright | Copyright Taylor & Francis Group, LLC 2009 Copyright Taylor & Francis Ltd. 2009 |
Copyright_xml | – notice: Copyright Taylor & Francis Group, LLC 2009 – notice: Copyright Taylor & Francis Ltd. 2009 |
DBID | AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D F28 FR3 |
DOI | 10.1080/08839510903207890 |
DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional ANTE: Abstracts in New Technology & Engineering Engineering Research Database |
DatabaseTitle | CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional Engineering Research Database ANTE: Abstracts in New Technology & Engineering |
DatabaseTitleList | Technology Research Database Computer and Information Systems Abstracts |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Computer Science |
EISSN | 1087-6545 |
EndPage | 711 |
ExternalDocumentID | 1884142051 10_1080_08839510903207890 420962 |
Genre | Original Articles |
GroupedDBID | .4S .7F .DC .QJ 0R~ 23M 2DF 30N 3YN 4.4 5GY 5VS 8VB AAAVI AAENE AAJMT ABBKH ABCCY ABDBF ABFIM ABHAV ABIVO ABJVF ABPEM ABPTK ABQHQ ABTAI ACGEJ ACGFS ACGOD ACNCT ACTIO ADCVX ADXPE AEGYZ AEISY AEMOZ AENEX AEOZL AEPSL AEYOC AFKVX AFOLD AGMYJ AHDLD AIJEM AIRXU AJWEG AKVCP ALMA_UNASSIGNED_HOLDINGS ALQZU AQRUH ARCSS AVBZW AWYRJ BLEHA CAG CCCUG CE4 COF CS3 DGEBU DKSSO EAP EBR EBS EBU ECS EDO EJD EMK EPL EST ESX E~A E~B F5P FPAXQ FUNRP FVPDL GTTXZ H13 HF~ HZ~ H~9 H~P I-F IPNFZ J.P KYCEM M4Z MK~ NA5 NX~ O9- P2P PQEST PQQKQ QWB RIG S-T SNACF TFL TFT TFW TH9 TNC TTHFI TUS TWF UT5 UU3 V1K ZL0 ~S~ 0YH AAYXX CITATION K1G 7SC 8FD JQ2 L7M L~C L~D F28 FR3 |
ID | FETCH-LOGICAL-c399t-510af3690299b774d95d40943a9e608b8af3fc04c9ded6ec42bc5319e22f7a203 |
ISSN | 0883-9514 |
IngestDate | Sat Oct 26 01:46:55 EDT 2024 Thu Oct 10 16:02:27 EDT 2024 Fri Aug 23 00:57:58 EDT 2024 Mon May 13 12:10:48 EDT 2019 Tue Jul 04 18:15:43 EDT 2023 |
IsDoiOpenAccess | false |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 7 |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c399t-510af3690299b774d95d40943a9e608b8af3fc04c9ded6ec42bc5319e22f7a203 |
Notes | ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 23 |
OpenAccessLink | https://www.tandfonline.com/doi/pdf/10.1080/08839510903207890?needAccess=true |
PQID | 215861250 |
PQPubID | 53050 |
PageCount | 18 |
ParticipantIDs | proquest_journals_215861250 proquest_miscellaneous_35012494 crossref_primary_10_1080_08839510903207890 informaworld_taylorfrancis_310_1080_08839510903207890 |
PublicationCentury | 2000 |
PublicationDate | 7/31/2009 |
PublicationDateYYYYMMDD | 2009-07-31 |
PublicationDate_xml | – month: 07 year: 2009 text: 7/31/2009 day: 31 |
PublicationDecade | 2000 |
PublicationPlace | Philadelphia |
PublicationPlace_xml | – name: Philadelphia |
PublicationTitle | Applied artificial intelligence |
PublicationYear | 2009 |
Publisher | Taylor & Francis Group Taylor & Francis Ltd |
Publisher_xml | – name: Taylor & Francis Group – name: Taylor & Francis Ltd |
References | Doi T. (CIT0007) 2005 Nomoto T. (CIT0016) 2004 Frederking R. (CIT0009) 1994 Stolcke A. (CIT0021) 2002 Nelder J. A. (CIT0015) 1965; 7 Costa-Jussà M. R. (CIT0003) 2006 Kneser R. (CIT0011) 1995; 1 Koehn P. (CIT0012) 2003 Crego J. M. (CIT0004) 2005 Crego J. M. (CIT0005) 2006 Jayaraman S. (CIT0010) 2005 Fiscus G. (CIT0008) 1997 Rosti A. V. I. (CIT0018) 2007 Matusov E. (CIT0014) 2006 Chen B. (CIT0002) 2005 CIT0013 Snover M. (CIT0020) 2006 Vilar D. (CIT0022) 2006 CIT0006 CIT0017 Sim K. C. (CIT0019) 2007; 4 Bangalore S. (CIT0001) 2001 |
References_xml | – start-page: 901 volume-title: Proc. of the 7th Int. Conf. on Spoken Language Processing, ICSLP'02 year: 2002 ident: CIT0021 contributor: fullname: Stolcke A. – volume-title: Proc. of the Int. Workshop on Spoken Language Translation, IWSLT'06 year: 2006 ident: CIT0003 contributor: fullname: Costa-Jussà M. R. – volume: 7 start-page: 308 year: 1965 ident: CIT0015 publication-title: The Computer Journal doi: 10.1093/comjnl/7.4.308 contributor: fullname: Nelder J. A. – start-page: 98 volume-title: Proc. of the Int. Workshop on Spoken Language Translation, IWSLT'05 year: 2005 ident: CIT0002 contributor: fullname: Chen B. – volume: 1 start-page: 181 volume-title: Proc. of the ICASSP Conference year: 1995 ident: CIT0011 contributor: fullname: Kneser R. – start-page: 177 volume-title: Proc. of the Int. Workshop on Spoken Language Translation, IWSLT'05 year: 2005 ident: CIT0004 contributor: fullname: Crego J. M. – volume-title: 4th Conference on Applied Natural Language Processing year: 1994 ident: CIT0009 contributor: fullname: Frederking R. – ident: CIT0017 doi: 10.1162/089120103321337421 – volume: 4 start-page: 105 volume-title: Proc. of the ICASSP year: 2007 ident: CIT0019 contributor: fullname: Sim K. C. – volume-title: Proc. of the Int. Workshop on Spoken Language Translation, IWSLT'06 year: 2006 ident: CIT0005 contributor: fullname: Crego J. M. – volume-title: IEEE Workshop on Automatic Speech Recognition and Understanding year: 1997 ident: CIT0008 contributor: fullname: Fiscus G. – ident: CIT0013 doi: 10.1162/coli.2006.32.4.527 – ident: CIT0006 – start-page: 228 volume-title: Proc. of the Human Language Technology Conf., HLT-NAACL'07 year: 2007 ident: CIT0018 contributor: fullname: Rosti A. V. I. – start-page: 48 volume-title: Proc. of the Human Language Technology Conf., HLT-NAACL'03 year: 2003 ident: CIT0012 contributor: fullname: Koehn P. – start-page: 697 volume-title: 5th Int. Conf. on Language Resources and Evaluation, LREC'06 year: 2006 ident: CIT0022 contributor: fullname: Vilar D. – start-page: 55 volume-title: Proc. of the Int. Workshop on Spoken Language Translation, IWSLT'04 year: 2005 ident: CIT0007 contributor: fullname: Doi T. – start-page: 33 volume-title: Proc. of the 11th Conf. of the European Chapter of the Association for Computational Linguistics year: 2006 ident: CIT0014 contributor: fullname: Matusov E. – start-page: 351 volume-title: IEEE Workshop on Automatic Speech Recognition and Understanding year: 2001 ident: CIT0001 contributor: fullname: Bangalore S. – start-page: 494 volume-title: Proc. of the 42th Annual Meeting of the Association for Computational Linguistics year: 2004 ident: CIT0016 contributor: fullname: Nomoto T. – start-page: 143 volume-title: 10th Conference of the European Association for Machine Translation year: 2005 ident: CIT0010 contributor: fullname: Jayaraman S. – volume-title: Proc. Assoc. for Machine Trans. in the Americas year: 2006 ident: CIT0020 contributor: fullname: Snover M. |
SSID | ssj0001771 |
Score | 1.8589754 |
Snippet | Multiples translations can be computed by one machine translation (MT) system or by different MT systems. We may assume that different MT systems make... |
SourceID | proquest crossref informaworld |
SourceType | Aggregation Database Enrichment Source Publisher |
StartPage | 694 |
SubjectTerms | Algorithms Artificial intelligence Information systems Translations Voice recognition |
Title | PHRASE AND NGRAM-BASED STATISTICAL MACHINE TRANSLATION SYSTEM COMBINATION |
URI | https://www.tandfonline.com/doi/abs/10.1080/08839510903207890 https://www.proquest.com/docview/215861250 https://search.proquest.com/docview/35012494 |
Volume | 23 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lj5swELaq7aWXvqum22196KkrKgeMg49sSpqsAlsFIqUnZMBIvYTVhkhVf_2OsXlkU0VtLyjBYAvP5_Fnj2cGoU_Co54jpGtJhwuLlsDhMiYpjCvOgB4Jz6PK3zmM2HxNrzfupt_MabxL6uxL_vuPfiX_I1W4B3JVXrL_INmuUrgBv0G-cAUJw_WvZPx9vvLjoIkQFX1b-aF1BX-_Asvzk0WcNJEOQn86X0TBZbLyo3ipc-zEP-IkCC-nN-HVIur3qNpYtIaXqvZMeImfg7idndGiAl5pXe93u8bWTozjTy36I4izSmWyrnbCmBq0UR5U0epgr4G3m5gGHclR2o_B2SOtsRwLKJveIZBaoxLQYszVMSNblatdjA20JgP9yXTG4yO9bg5CQv2KEXKV9V158PaTWGu4j27S2Xq5TJNgkxyW6iUPYG9MbaKc7h_boJuUUnRI1E3e40mzRu--pDWEq3DsD1s_oDIHgW6PJvaGrSTP0VOzzMC-xswL9EhuX6JnbQoPbDT6K7TQEMIAITyAEB5ACBsI4QGEsIYQHkDoNVrPgmQ6t0x2DSsHUlpb8CWidBgnQEgyWAQU3C3UYt8RXDLiZR6UljmhOS9kwWRO7SxXClvadjkRNnHeoLNttZVvEc4deJgUE8IzRmXucjrmhUdKLmjJae6N0Oe2o9JbHUQlHbexaR_26giRYVemdQO6UuPt-PG0_lWPkHviFedEU-etmFIzrHcpcGBP0X4o_diVgs5VhjSxldUeanSJytlO3518_xw96cfQe3RW3-3lBTDYOvvQYO4eskOHjw |
link.rule.ids | 315,783,787,27936,27937,60214,61003 |
linkProvider | Taylor & Francis |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT9wwEB4VeigXoC-xPH3oqVKod-Nk7WNYFpJ2k1abINFT5DjOBWlBkJUQv56ZPBAvceAYeWI7sWf8zdj-BuCHlkK62nqOdZV2RIUYrvCtQL1SPsIjLaWg-85x4odn4ve5d94F3G66Y5XkQ1ctUURjq0m5KRjdH4n7hZrhEjJQlP2bbnKuwEefyL_oCgdPHizxcNw4XCTuoLzodzVfq-LJuvSEtfSFlW6WnpMNyPtOtydOLg6XdXFo7p7xOb7_qzZhvUOlLGin0Wf4YBdfYKPP-MA6A_AVon_hPEinLEiOWXI6D2LnCB-PWZoFWZRmxK3A4mASRsmUZfMgSWdNCIyl_9NsGrPJ3_goavl3v8HZyTSbhE6XjMExiGFqBzumKxd9aVy_CsSMpfJK8g1drazPZSGxtDJcGFXa0rdGjApD-m1Ho2qsR9z9DquLy4XdAmZcFOblmKvCF9Z4SgxVKXmltKiUMHIAP_uhyK9azo182FOZPv9JA-CPByuvm0BH1WYleSme17f1ALw3XnHfaGqnnwh5p-k3OUImSSgRSw8eSlFFad9FL-zlEmv0OKX4FtvvbPcAPoVZPMtnUfJnB9ba_SyKLu_Can29tHsIi-piv5n797MU-ak |
linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8QgECY-EuPFt3F9cvBkUmUX2oVj3YdbtdVsa6KnhlK4mKzG7SbGX-_Qh_EVDx4bplDKDHwDwzcIHUvOOJXadTQV0mEGMFzmaQZ2JTyAR5JzZu87h5E3umOX9-59HZszrcMqrQ9tKqKIcq62xv2cmyYi7gwMg1pgIGzyb3uRcx4tAgogVs0piT4m4na39LesuAPyrDnU_K2KL8vSF9LSH5N0ufIMV6v0qtOSsNAGnDyezorsVL19o3P8d6fW0EqNSbFfKdE6mtOTDbTa5HvAtflvouB2NPbjAfajPo4uxn7onMNjH8eJnwRxYpkVcOj3RkE0wMnYj-LrcgMMxw9xMghx7yY8Dyr23S10NxwkvZFTp2JwFCCYwoEPk4aCJw2rVwaIMRdubj1DKoX2CM84lBpFmBK5zj2tWCdT1rp1p2O6skPoNlqYPE30DsKKgjDJu0RkHtPKFawtck6MkMwIpngLnTQjkT5XjBtpuyEy_f6TWoh8Hqu0KLc5TJWT5Kd4WrwWLeT-8Qr9o6m9Rg_S2s6nKQAmbjEilB59lIKB2lMXOdFPM6jRJTbBN9v9Z7tHaOm2P0yvg-hqDy1Xh1l2a3kfLRQvM30AmKjIDkvNfwemg_hW |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=PHRASE+AND+NGRAM-BASED+STATISTICAL+MACHINE+TRANSLATION+SYSTEM+COMBINATION&rft.jtitle=Applied+artificial+intelligence&rft.au=Costa-Juss%C3%A0%2C+Marta+R&rft.au=Fonollosa%2C+Jos%C3%A9+A+R&rft.date=2009-07-31&rft.pub=Taylor+%26+Francis+Ltd&rft.issn=0883-9514&rft.eissn=1087-6545&rft.volume=23&rft.issue=7&rft.spage=694&rft_id=info:doi/10.1080%2F08839510903207890&rft.externalDBID=NO_FULL_TEXT&rft.externalDocID=1884142051 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0883-9514&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0883-9514&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0883-9514&client=summon |