A neural reordering model based on phrasal dependency tree for statistical machine translation
Machine translation is an important field of research and development. Word reordering is one of the main problems in machine translation. It is an important factor of quality and efficiency of machine translations and becomes more difficult when it deals with structurally divergent language pairs....
Saved in:
Published in | Intelligent data analysis Vol. 22; no. 5; pp. 1163 - 1183 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Amsterdam
IOS Press BV
01.01.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Machine translation is an important field of research and development. Word reordering is one of the main problems in machine translation. It is an important factor of quality and efficiency of machine translations and becomes more difficult when it deals with structurally divergent language pairs. To overcome this problem, we introduce a neural reordering model, using phrasal dependency trees which depict dependency relations among contiguous non-syntactic phrases. The model makes the use of reordering rules, which are automatically learned by a probabilistic neural network classifier from a reordered phrasal dependency tree bank. The proposed model combines the power of the lexical reordering and syntactic pre-ordering models by performing long-distance reorderings. The proposed reordering model is integrated into a standard phrase-based statistical machine translation system to translate input sentences. Our method is evaluated on syntactically divergent language-pairs, English → Persian and English → German using WMT07 benchmark. The results illustrate the superiority of the proposed method in terms of BLEU, TER and LRscore on both translation tasks. On average the proposed method retrieves a significant impact on precision and recall values respect to the hierarchical, lexicalized and distortion reordering models. |
---|---|
AbstractList | Machine translation is an important field of research and development. Word reordering is one of the main problems in machine translation. It is an important factor of quality and efficiency of machine translations and becomes more difficult when it deals with structurally divergent language pairs. To overcome this problem, we introduce a neural reordering model, using phrasal dependency trees which depict dependency relations among contiguous non-syntactic phrases. The model makes the use of reordering rules, which are automatically learned by a probabilistic neural network classifier from a reordered phrasal dependency tree bank. The proposed model combines the power of the lexical reordering and syntactic pre-ordering models by performing long-distance reorderings. The proposed reordering model is integrated into a standard phrase-based statistical machine translation system to translate input sentences. Our method is evaluated on syntactically divergent language-pairs, English → Persian and English → German using WMT07 benchmark. The results illustrate the superiority of the proposed method in terms of BLEU, TER and LRscore on both translation tasks. On average the proposed method retrieves a significant impact on precision and recall values respect to the hierarchical, lexicalized and distortion reordering models. |
Author | Farzi, Saeed Faili, Heshaam Kianian, Sahar |
Author_xml | – sequence: 1 givenname: Saeed surname: Farzi fullname: Farzi, Saeed organization: Faculty of Computer Engineering, K. N. Toosi University of Technology, Tehran, Iran – sequence: 2 givenname: Heshaam surname: Faili fullname: Faili, Heshaam organization: School of Electrical and Computer Engineering, Tehran University, Tehran, Iran – sequence: 3 givenname: Sahar surname: Kianian fullname: Kianian, Sahar organization: Faculty of Computer Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran |
BookMark | eNotkE1LAzEQhoMo2FYv_oKAN2E12Uk2u8dSvwoFLwqeDNnNxG7ZJmuyPfTfG6nMYYZ5H2bgmZNzHzwScsPZPZQAD-vHZcEVyLo8IzMuFS8EL-vzPLO6LkSlPi_JPKUdY0yUTMzI15J6PEQz0IghWoy9_6b7YHGgrUloafB03EaTMmFxRG_Rd0c6RUTqQqRpMlOfpr7L-d50295jDo1PQ94Hf0UunBkSXv_3Bfl4fnpfvRabt5f1arkpulI2U1FxgU3lFEKDFoQVnLmqdKK2xrJGSpMLrFSigg6hkgpb1YIVrlVc1QxgQW5Pd8cYfg6YJr0Lh-jzS11yDkpAAzJTdyeqiyGliE6Psd-beNSc6T9_OvvTJ3_wC40UZKg |
CitedBy_id | crossref_primary_10_1142_S0219649222400275 |
Cites_doi | 10.3115/1220175.1220241 10.3115/1219840.1219906 10.3115/1219840.1219873 10.5715/jnlp.21.485 10.3115/1626281.1626282 10.3115/1075218.1075274 10.3115/1699571.1699644 10.3115/1073445.1073462 10.1145/2499955.2499960 10.1016/j.csl.2006.09.003 10.1016/j.csl.2011.01.001 10.1145/1390156.1390177 10.3115/1557769.1557821 10.3115/1075096.1075117 10.1016/j.csl.2014.07.002 10.1609/aaai.v25i1.7917 10.1109/AISP.2012.6313739 10.1007/3-540-33486-6_6 10.3115/1219840.1219874 10.13053/rcs-65-1-4 10.1145/2518100 10.1162/coli.2007.33.2.201 10.3115/1626394.1626401 10.1162/0891201042544884 10.3115/1626431.1626472 |
ContentType | Journal Article |
Copyright | Copyright IOS Press BV 2018 |
Copyright_xml | – notice: Copyright IOS Press BV 2018 |
DBID | AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D |
DOI | 10.3233/IDA-173582 |
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 |
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 |
DatabaseTitleList | Computer and Information Systems Abstracts |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Mathematics Computer Science |
EISSN | 1571-4128 |
EndPage | 1183 |
ExternalDocumentID | 10_3233_IDA_173582 |
GroupedDBID | 0R~ 4.4 5GY 8VB AAYXX ABDBF ABIVO ABJNI ACGFS ACPQW ADZMO AEMOZ AENEX AFRHK AKVCP ALMA_UNASSIGNED_HOLDINGS ASPBG AVWKF CITATION CS3 E.- EAD EAP EBA EBR EBS EBU EIS EJD EMK EPL EST ESX FDB HZ~ I-F IOS K1G MET MIO MK~ ML~ MV1 NGNOM O9- P2P PQQKQ QWB TH9 TUS ZL0 7SC 8FD JQ2 L7M L~C L~D |
ID | FETCH-LOGICAL-c259t-614e96f7e39ed34d410f62f48dad0955a5a53d57463ce3657eb7b3d4fb7178033 |
ISSN | 1088-467X |
IngestDate | Thu Oct 10 17:49:23 EDT 2024 Fri Aug 23 01:14:06 EDT 2024 |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 5 |
Language | English |
LinkModel | OpenURL |
MergedId | FETCHMERGED-LOGICAL-c259t-614e96f7e39ed34d410f62f48dad0955a5a53d57463ce3657eb7b3d4fb7178033 |
PQID | 2113743935 |
PQPubID | 2046397 |
PageCount | 21 |
ParticipantIDs | proquest_journals_2113743935 crossref_primary_10_3233_IDA_173582 |
PublicationCentury | 2000 |
PublicationDate | 2018-01-01 |
PublicationDateYYYYMMDD | 2018-01-01 |
PublicationDate_xml | – month: 01 year: 2018 text: 2018-01-01 day: 01 |
PublicationDecade | 2010 |
PublicationPlace | Amsterdam |
PublicationPlace_xml | – name: Amsterdam |
PublicationTitle | Intelligent data analysis |
PublicationYear | 2018 |
Publisher | IOS Press BV |
Publisher_xml | – name: IOS Press BV |
References | 10.3233/IDA-173582_ref51 10.3233/IDA-173582_ref30 10.3233/IDA-173582_ref52 10.3233/IDA-173582_ref33 10.3233/IDA-173582_ref55 10.3233/IDA-173582_ref12 10.3233/IDA-173582_ref56 10.3233/IDA-173582_ref31 10.3233/IDA-173582_ref10 10.3233/IDA-173582_ref32 10.3233/IDA-173582_ref54 Habash (10.3233/IDA-173582_ref22) 2007 Farzi (10.3233/IDA-173582_ref40) 2015; 29 Khalilov (10.3233/IDA-173582_ref5) 2011; 25 10.3233/IDA-173582_ref6 10.3233/IDA-173582_ref8 10.3233/IDA-173582_ref9 10.3233/IDA-173582_ref26 10.3233/IDA-173582_ref27 10.3233/IDA-173582_ref49 10.3233/IDA-173582_ref24 10.3233/IDA-173582_ref46 10.3233/IDA-173582_ref1 10.3233/IDA-173582_ref25 10.3233/IDA-173582_ref47 10.3233/IDA-173582_ref3 10.3233/IDA-173582_ref28 10.3233/IDA-173582_ref29 Chiang (10.3233/IDA-173582_ref21) 2007; 33 10.3233/IDA-173582_ref23 10.3233/IDA-173582_ref45 10.3233/IDA-173582_ref42 Och (10.3233/IDA-173582_ref50) 2004; 30 10.3233/IDA-173582_ref43 Schwenk (10.3233/IDA-173582_ref48) 2007; 21 Farzi (10.3233/IDA-173582_ref4) 2013; 65 10.3233/IDA-173582_ref15 10.3233/IDA-173582_ref37 10.3233/IDA-173582_ref38 10.3233/IDA-173582_ref13 10.3233/IDA-173582_ref35 10.3233/IDA-173582_ref57 10.3233/IDA-173582_ref14 10.3233/IDA-173582_ref36 10.3233/IDA-173582_ref19 10.3233/IDA-173582_ref39 10.3233/IDA-173582_ref18 Collobert (10.3233/IDA-173582_ref44) 2011; 12 |
References_xml | – ident: 10.3233/IDA-173582_ref6 – ident: 10.3233/IDA-173582_ref56 – ident: 10.3233/IDA-173582_ref12 doi: 10.3115/1220175.1220241 – ident: 10.3233/IDA-173582_ref31 – ident: 10.3233/IDA-173582_ref8 – ident: 10.3233/IDA-173582_ref26 doi: 10.3115/1219840.1219906 – ident: 10.3233/IDA-173582_ref39 doi: 10.3115/1219840.1219873 – ident: 10.3233/IDA-173582_ref32 doi: 10.5715/jnlp.21.485 – ident: 10.3233/IDA-173582_ref10 doi: 10.3115/1626281.1626282 – ident: 10.3233/IDA-173582_ref54 doi: 10.3115/1075218.1075274 – ident: 10.3233/IDA-173582_ref9 doi: 10.3115/1699571.1699644 – ident: 10.3233/IDA-173582_ref1 doi: 10.3115/1073445.1073462 – ident: 10.3233/IDA-173582_ref46 – ident: 10.3233/IDA-173582_ref27 – ident: 10.3233/IDA-173582_ref35 doi: 10.1145/2499955.2499960 – ident: 10.3233/IDA-173582_ref25 – volume: 21 start-page: 492 year: 2007 ident: 10.3233/IDA-173582_ref48 article-title: Continuous space language models publication-title: Computer Speech & Language doi: 10.1016/j.csl.2006.09.003 contributor: fullname: Schwenk – volume: 25 start-page: 761 year: 2011 ident: 10.3233/IDA-173582_ref5 article-title: Syntax-based reordering for statistical machine translation publication-title: Computer Speech & Language doi: 10.1016/j.csl.2011.01.001 contributor: fullname: Khalilov – ident: 10.3233/IDA-173582_ref14 – ident: 10.3233/IDA-173582_ref37 – ident: 10.3233/IDA-173582_ref43 doi: 10.1145/1390156.1390177 – ident: 10.3233/IDA-173582_ref3 doi: 10.3115/1557769.1557821 – ident: 10.3233/IDA-173582_ref57 doi: 10.3115/1075096.1075117 – ident: 10.3233/IDA-173582_ref52 – volume: 29 start-page: 45 year: 2015 ident: 10.3233/IDA-173582_ref40 article-title: A swarm-inspired re-ranker system for statistical machine translation publication-title: Computer Speech & Language doi: 10.1016/j.csl.2014.07.002 contributor: fullname: Farzi – ident: 10.3233/IDA-173582_ref42 doi: 10.1609/aaai.v25i1.7917 – ident: 10.3233/IDA-173582_ref51 doi: 10.1109/AISP.2012.6313739 – ident: 10.3233/IDA-173582_ref55 – ident: 10.3233/IDA-173582_ref18 doi: 10.1007/3-540-33486-6_6 – ident: 10.3233/IDA-173582_ref36 doi: 10.3115/1219840.1219874 – volume: 65 start-page: 51 year: 2013 ident: 10.3233/IDA-173582_ref4 article-title: A Novel Reordering Model for Statistical Machine Translation publication-title: Research in Computing Science doi: 10.13053/rcs-65-1-4 contributor: fullname: Farzi – ident: 10.3233/IDA-173582_ref49 – ident: 10.3233/IDA-173582_ref33 doi: 10.1145/2518100 – volume: 33 start-page: 201 year: 2007 ident: 10.3233/IDA-173582_ref21 article-title: Hierarchical phrase-based translation publication-title: Computational Linguistics doi: 10.1162/coli.2007.33.2.201 contributor: fullname: Chiang – ident: 10.3233/IDA-173582_ref47 – ident: 10.3233/IDA-173582_ref24 – ident: 10.3233/IDA-173582_ref45 – ident: 10.3233/IDA-173582_ref19 – ident: 10.3233/IDA-173582_ref28 doi: 10.3115/1626394.1626401 – volume: 30 start-page: 417 year: 2004 ident: 10.3233/IDA-173582_ref50 article-title: The alignment template approach to statistical machine translation publication-title: Computational Linguistics doi: 10.1162/0891201042544884 contributor: fullname: Och – ident: 10.3233/IDA-173582_ref23 doi: 10.5715/jnlp.21.485 – volume: 12 start-page: 2493 year: 2011 ident: 10.3233/IDA-173582_ref44 article-title: Natural language processing (almost) from scratch publication-title: The Journal of Machine Learning Research contributor: fullname: Collobert – ident: 10.3233/IDA-173582_ref13 – start-page: 215 year: 2007 ident: 10.3233/IDA-173582_ref22 article-title: Syntactic preprocessing for statistical machine translation publication-title: MT Summit XI contributor: fullname: Habash – ident: 10.3233/IDA-173582_ref38 – ident: 10.3233/IDA-173582_ref30 – ident: 10.3233/IDA-173582_ref15 – ident: 10.3233/IDA-173582_ref29 doi: 10.3115/1626431.1626472 |
SSID | ssj0004204 |
Score | 2.1959596 |
Snippet | Machine translation is an important field of research and development. Word reordering is one of the main problems in machine translation. It is an important... |
SourceID | proquest crossref |
SourceType | Aggregation Database |
StartPage | 1163 |
SubjectTerms | Dependence Machine translation Neural networks R&D Research & development Sentences Statistical analysis Translations |
Title | A neural reordering model based on phrasal dependency tree for statistical machine translation |
URI | https://www.proquest.com/docview/2113743935 |
Volume | 22 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3Pb9MwFLagu8CBHwPEYCBLcKsCSezEyTFjVAVpnDapJyL_iiiCDLXZYfvrec9242xwGKhS1Fpyqub7-uz3_N73CHnLgLhV1XWJlNomXBY2kVUnkjovha00F6nG0MDJl3J5xj-vilVMK3LVJYN6p6_-WlfyP6jCGOCKVbL_gOx4UxiA94AvXAFhuN4K42aOcpROmt9JaKLb71rbzHFxMngQAFjJLR7EhGa3-hJzy73SNxYTOZ1mrCBxSZUWW0b02x8Rru8x090rdw5zTCqdyyBmMuIvN1drH2K2oV7Kja59-fUST5bkz3jiL_t1CL3Kb3IzjT1k1ST24M0l2KgETO3KrybBhArwSrNQ8h1sbJ5PuFRMDGaWBftmw0ff1uamYWc5Bp4Xn46bJBNY3BuXr92R_Y1Vbcw1BC8HZ7cwt_Vz75K9XNRFMSN7zdHx0SLW0eau3eT4q7ycLc5-H7_5-gbm-vrtNiWnj8iD4E3QxlPjMblj-33ycNepgwbDvU_un4zqvNsn5GtDPW9o5A11vKGON_S8p4E3NPKGIm8o8IZOeEMDb-iEN0_J2eLj6YdlEvpsJBqc3yGBHZqty05YVlvDuOFZ2pV5xysjDSoUSngxUwheMm1ZWQirhGKGd0pkokoZe0Zm_XlvnxPaqdSk3BqFjnrFVFV2teaqVkwLKWp9QN7sHl77y8uptH8CdEAOd8-1DX-3bZtnGUPvmRUvbnWTl-RepOwhmQ2bC_sKNpCDeh1w_w3QQ3Mw |
link.rule.ids | 315,786,790,27955,27956 |
linkProvider | EBSCOhost |
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=A+neural+reordering+model+based+on+phrasal+dependency+tree+for+statistical+machine+translation&rft.jtitle=Intelligent+data+analysis&rft.au=Farzi%2C+Saeed&rft.au=Faili%2C+Heshaam&rft.au=Kianian%2C+Sahar&rft.date=2018-01-01&rft.issn=1088-467X&rft.eissn=1571-4128&rft.volume=22&rft.issue=5&rft.spage=1163&rft.epage=1183&rft_id=info:doi/10.3233%2FIDA-173582&rft.externalDBID=n%2Fa&rft.externalDocID=10_3233_IDA_173582 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1088-467X&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1088-467X&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1088-467X&client=summon |