The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation
This paper describes the use of a statistical structural N-gram model in the natural language generation component of a Spanish-English generation-heavy hybrid machine translation system. A structural N-gram model captures the relationship between words in a dependency representation without taking...
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Buchkapitel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 69 |
|---|---|
| container_issue | |
| container_start_page | 61 |
| container_title | |
| container_volume | 3123 |
| creator | Habash, Nizar |
| description | This paper describes the use of a statistical structural N-gram model in the natural language generation component of a Spanish-English generation-heavy hybrid machine translation system. A structural N-gram model captures the relationship between words in a dependency representation without taking into account the overall structure at the phrase level. The model is used together with other components in the system for lexical and structural selection. An evaluation of the machine translation system shows that the use of structural N-grams decreases runtime by 60% with no loss in translation quality. |
| doi_str_mv | 10.1007/978-3-540-27823-8_7 |
| format | Book Chapter |
| fullrecord | <record><control><sourceid>proquest_pasca</sourceid><recordid>TN_cdi_pascalfrancis_primary_15993488</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EBC3088236_13_69</sourcerecordid><originalsourceid>FETCH-LOGICAL-p270t-9e30d0e696ffb9e3c07b376e4d4c5d09d869ada7c096ef853b9cd636876ff9ee3</originalsourceid><addsrcrecordid>eNotkE1v2zAMhrV1HZZ2-QW76LKjVsq09XEsijYZkGyHJrcBgizTiTvXTiVnQP791LS8EBSflxAexr5J-CEB9I3VRqCoShCFNgUK4_QHdoX54TzDRzaTSkqBWNoLNs_4eVdgCdUnNgOEQlhd4mc2sxkxoEr9hc1TeoJcBRiFdsb-bPbEt4n42HLPH6d4DNMx-p7_Ervon_nKD7uj3xFfjw31vBv4ggaKfurGQSzJ_zvx5amOXcPXPuy7gfgm-iH1Z-Aru2x9n2j-3q_Z9uF-c7cUq9-Ln3e3K3EoNEzCEkIDpKxq2zoPAXSNWlHZlKFqwDZGWd94HcAqak2FtQ2NQmV0DlgivGbf3-4efAq-b_MPQpfcIXbPPp6crGw2YEzm5BuX8mrYUXT1OP5NToJ7Ve6yQ4cuW3RnxS4rz5ni_XYcX46UJkevoUDDlDWFvT9MFJNDMDmhnESnLP4HbwF-vA</addsrcrecordid><sourcetype>Index Database</sourcetype><iscdi>true</iscdi><recordtype>book_chapter</recordtype><pqid>EBC3088236_13_69</pqid></control><display><type>book_chapter</type><title>The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation</title><source>Springer Books</source><creator>Habash, Nizar</creator><contributor>Evans, Roger ; Belz, Anja ; Piwek, Paul ; Piwek, Paul ; Belz, Anja ; Evans, Roger</contributor><creatorcontrib>Habash, Nizar ; Evans, Roger ; Belz, Anja ; Piwek, Paul ; Piwek, Paul ; Belz, Anja ; Evans, Roger</creatorcontrib><description>This paper describes the use of a statistical structural N-gram model in the natural language generation component of a Spanish-English generation-heavy hybrid machine translation system. A structural N-gram model captures the relationship between words in a dependency representation without taking into account the overall structure at the phrase level. The model is used together with other components in the system for lexical and structural selection. An evaluation of the machine translation system shows that the use of structural N-grams decreases runtime by 60% with no loss in translation quality.</description><identifier>ISSN: 0302-9743</identifier><identifier>ISBN: 9783540223405</identifier><identifier>ISBN: 3540223401</identifier><identifier>EISSN: 1611-3349</identifier><identifier>EISBN: 3540278230</identifier><identifier>EISBN: 9783540278238</identifier><identifier>DOI: 10.1007/978-3-540-27823-8_7</identifier><identifier>OCLC: 934980647</identifier><identifier>LCCallNum: QA76.9.N38</identifier><language>eng</language><publisher>Germany: Springer Berlin / Heidelberg</publisher><subject>Applied sciences ; Artificial intelligence ; Computational Linguistics ; Computer science; control theory; systems ; Exact sciences and technology ; Machine Translation ; Natural Language Generation ; Speech and sound recognition and synthesis. Linguistics ; Thematic Role ; Translation Quality</subject><ispartof>Lecture notes in computer science, 2004, Vol.3123, p.61-69</ispartof><rights>Springer-Verlag Berlin Heidelberg 2004</rights><rights>2004 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><relation>Lecture Notes in Computer Science</relation></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttps://ebookcentral.proquest.com/covers/3088236-l.jpg</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/978-3-540-27823-8_7$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/978-3-540-27823-8_7$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>309,310,775,776,780,785,786,789,4036,4037,27902,38232,41418,42487</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=15993488$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><contributor>Evans, Roger</contributor><contributor>Belz, Anja</contributor><contributor>Piwek, Paul</contributor><contributor>Piwek, Paul</contributor><contributor>Belz, Anja</contributor><contributor>Evans, Roger</contributor><creatorcontrib>Habash, Nizar</creatorcontrib><title>The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation</title><title>Lecture notes in computer science</title><description>This paper describes the use of a statistical structural N-gram model in the natural language generation component of a Spanish-English generation-heavy hybrid machine translation system. A structural N-gram model captures the relationship between words in a dependency representation without taking into account the overall structure at the phrase level. The model is used together with other components in the system for lexical and structural selection. An evaluation of the machine translation system shows that the use of structural N-grams decreases runtime by 60% with no loss in translation quality.</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Computational Linguistics</subject><subject>Computer science; control theory; systems</subject><subject>Exact sciences and technology</subject><subject>Machine Translation</subject><subject>Natural Language Generation</subject><subject>Speech and sound recognition and synthesis. Linguistics</subject><subject>Thematic Role</subject><subject>Translation Quality</subject><issn>0302-9743</issn><issn>1611-3349</issn><isbn>9783540223405</isbn><isbn>3540223401</isbn><isbn>3540278230</isbn><isbn>9783540278238</isbn><fulltext>true</fulltext><rsrctype>book_chapter</rsrctype><creationdate>2004</creationdate><recordtype>book_chapter</recordtype><recordid>eNotkE1v2zAMhrV1HZZ2-QW76LKjVsq09XEsijYZkGyHJrcBgizTiTvXTiVnQP791LS8EBSflxAexr5J-CEB9I3VRqCoShCFNgUK4_QHdoX54TzDRzaTSkqBWNoLNs_4eVdgCdUnNgOEQlhd4mc2sxkxoEr9hc1TeoJcBRiFdsb-bPbEt4n42HLPH6d4DNMx-p7_Ervon_nKD7uj3xFfjw31vBv4ggaKfurGQSzJ_zvx5amOXcPXPuy7gfgm-iH1Z-Aru2x9n2j-3q_Z9uF-c7cUq9-Ln3e3K3EoNEzCEkIDpKxq2zoPAXSNWlHZlKFqwDZGWd94HcAqak2FtQ2NQmV0DlgivGbf3-4efAq-b_MPQpfcIXbPPp6crGw2YEzm5BuX8mrYUXT1OP5NToJ7Ve6yQ4cuW3RnxS4rz5ni_XYcX46UJkevoUDDlDWFvT9MFJNDMDmhnESnLP4HbwF-vA</recordid><startdate>2004</startdate><enddate>2004</enddate><creator>Habash, Nizar</creator><general>Springer Berlin / Heidelberg</general><general>Springer Berlin Heidelberg</general><general>Springer</general><scope>FFUUA</scope><scope>IQODW</scope></search><sort><creationdate>2004</creationdate><title>The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation</title><author>Habash, Nizar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-p270t-9e30d0e696ffb9e3c07b376e4d4c5d09d869ada7c096ef853b9cd636876ff9ee3</frbrgroupid><rsrctype>book_chapters</rsrctype><prefilter>book_chapters</prefilter><language>eng</language><creationdate>2004</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Computational Linguistics</topic><topic>Computer science; control theory; systems</topic><topic>Exact sciences and technology</topic><topic>Machine Translation</topic><topic>Natural Language Generation</topic><topic>Speech and sound recognition and synthesis. Linguistics</topic><topic>Thematic Role</topic><topic>Translation Quality</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Habash, Nizar</creatorcontrib><collection>ProQuest Ebook Central - Book Chapters - Demo use only</collection><collection>Pascal-Francis</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Habash, Nizar</au><au>Evans, Roger</au><au>Belz, Anja</au><au>Piwek, Paul</au><au>Piwek, Paul</au><au>Belz, Anja</au><au>Evans, Roger</au><format>book</format><genre>bookitem</genre><ristype>CHAP</ristype><atitle>The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation</atitle><btitle>Lecture notes in computer science</btitle><seriestitle>Lecture Notes in Computer Science</seriestitle><date>2004</date><risdate>2004</risdate><volume>3123</volume><spage>61</spage><epage>69</epage><pages>61-69</pages><issn>0302-9743</issn><eissn>1611-3349</eissn><isbn>9783540223405</isbn><isbn>3540223401</isbn><eisbn>3540278230</eisbn><eisbn>9783540278238</eisbn><abstract>This paper describes the use of a statistical structural N-gram model in the natural language generation component of a Spanish-English generation-heavy hybrid machine translation system. A structural N-gram model captures the relationship between words in a dependency representation without taking into account the overall structure at the phrase level. The model is used together with other components in the system for lexical and structural selection. An evaluation of the machine translation system shows that the use of structural N-grams decreases runtime by 60% with no loss in translation quality.</abstract><cop>Germany</cop><pub>Springer Berlin / Heidelberg</pub><doi>10.1007/978-3-540-27823-8_7</doi><oclcid>934980647</oclcid><tpages>9</tpages></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0302-9743 |
| ispartof | Lecture notes in computer science, 2004, Vol.3123, p.61-69 |
| issn | 0302-9743 1611-3349 |
| language | eng |
| recordid | cdi_pascalfrancis_primary_15993488 |
| source | Springer Books |
| subjects | Applied sciences Artificial intelligence Computational Linguistics Computer science control theory systems Exact sciences and technology Machine Translation Natural Language Generation Speech and sound recognition and synthesis. Linguistics Thematic Role Translation Quality |
| title | The Use of a Structural N-gram Language Model in Generation-Heavy Hybrid Machine Translation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-29T14%3A28%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pasca&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=bookitem&rft.atitle=The%20Use%20of%20a%20Structural%20N-gram%20Language%20Model%20in%20Generation-Heavy%20Hybrid%20Machine%20Translation&rft.btitle=Lecture%20notes%20in%20computer%20science&rft.au=Habash,%20Nizar&rft.date=2004&rft.volume=3123&rft.spage=61&rft.epage=69&rft.pages=61-69&rft.issn=0302-9743&rft.eissn=1611-3349&rft.isbn=9783540223405&rft.isbn_list=3540223401&rft_id=info:doi/10.1007/978-3-540-27823-8_7&rft_dat=%3Cproquest_pasca%3EEBC3088236_13_69%3C/proquest_pasca%3E%3Curl%3E%3C/url%3E&rft.eisbn=3540278230&rft.eisbn_list=9783540278238&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=EBC3088236_13_69&rft_id=info:pmid/&rfr_iscdi=true |