MACHINE TRANSLATION USING NEURAL NETWORK MODELS
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural ne...
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Hughes, Macduff Richard Parmar, Niki J Foster, George Bapna, Ankur Johnson Premkumar, Melvin Jose Chen, Xu Jones, Llion Owen Firat, Orhan Macherey, Wolfgang Schuster, Michael Wu, Yonghui Chen, Zhifeng |
| description | Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2020034436A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2020034436A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2020034436A13</originalsourceid><addsrcrecordid>eNrjZND3dXT28PRzVQgJcvQL9nEM8fT3UwgN9vRzV_BzDQ1y9AFSIeH-Qd4Kvv4urj7BPAysaYk5xam8UJqbQdnNNcTZQze1ID8-tbggMTk1L7UkPjTYyMDIwMDYxMTYzNHQmDhVALaUJxk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>MACHINE TRANSLATION USING NEURAL NETWORK MODELS</title><source>esp@cenet</source><creator>Hughes, Macduff Richard ; Parmar, Niki J ; Foster, George ; Bapna, Ankur ; Johnson Premkumar, Melvin Jose ; Chen, Xu ; Jones, Llion Owen ; Firat, Orhan ; Macherey, Wolfgang ; Schuster, Michael ; Wu, Yonghui ; Chen, Zhifeng</creator><creatorcontrib>Hughes, Macduff Richard ; Parmar, Niki J ; Foster, George ; Bapna, Ankur ; Johnson Premkumar, Melvin Jose ; Chen, Xu ; Jones, Llion Owen ; Firat, Orhan ; Macherey, Wolfgang ; Schuster, Michael ; Wu, Yonghui ; Chen, Zhifeng</creatorcontrib><description>Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2020</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200130&DB=EPODOC&CC=US&NR=2020034436A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200130&DB=EPODOC&CC=US&NR=2020034436A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>Hughes, Macduff Richard</creatorcontrib><creatorcontrib>Parmar, Niki J</creatorcontrib><creatorcontrib>Foster, George</creatorcontrib><creatorcontrib>Bapna, Ankur</creatorcontrib><creatorcontrib>Johnson Premkumar, Melvin Jose</creatorcontrib><creatorcontrib>Chen, Xu</creatorcontrib><creatorcontrib>Jones, Llion Owen</creatorcontrib><creatorcontrib>Firat, Orhan</creatorcontrib><creatorcontrib>Macherey, Wolfgang</creatorcontrib><creatorcontrib>Schuster, Michael</creatorcontrib><creatorcontrib>Wu, Yonghui</creatorcontrib><creatorcontrib>Chen, Zhifeng</creatorcontrib><title>MACHINE TRANSLATION USING NEURAL NETWORK MODELS</title><description>Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZND3dXT28PRzVQgJcvQL9nEM8fT3UwgN9vRzV_BzDQ1y9AFSIeH-Qd4Kvv4urj7BPAysaYk5xam8UJqbQdnNNcTZQze1ID8-tbggMTk1L7UkPjTYyMDIwMDYxMTYzNHQmDhVALaUJxk</recordid><startdate>20200130</startdate><enddate>20200130</enddate><creator>Hughes, Macduff Richard</creator><creator>Parmar, Niki J</creator><creator>Foster, George</creator><creator>Bapna, Ankur</creator><creator>Johnson Premkumar, Melvin Jose</creator><creator>Chen, Xu</creator><creator>Jones, Llion Owen</creator><creator>Firat, Orhan</creator><creator>Macherey, Wolfgang</creator><creator>Schuster, Michael</creator><creator>Wu, Yonghui</creator><creator>Chen, Zhifeng</creator><scope>EVB</scope></search><sort><creationdate>20200130</creationdate><title>MACHINE TRANSLATION USING NEURAL NETWORK MODELS</title><author>Hughes, Macduff Richard ; Parmar, Niki J ; Foster, George ; Bapna, Ankur ; Johnson Premkumar, Melvin Jose ; Chen, Xu ; Jones, Llion Owen ; Firat, Orhan ; Macherey, Wolfgang ; Schuster, Michael ; Wu, Yonghui ; Chen, Zhifeng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2020034436A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>Hughes, Macduff Richard</creatorcontrib><creatorcontrib>Parmar, Niki J</creatorcontrib><creatorcontrib>Foster, George</creatorcontrib><creatorcontrib>Bapna, Ankur</creatorcontrib><creatorcontrib>Johnson Premkumar, Melvin Jose</creatorcontrib><creatorcontrib>Chen, Xu</creatorcontrib><creatorcontrib>Jones, Llion Owen</creatorcontrib><creatorcontrib>Firat, Orhan</creatorcontrib><creatorcontrib>Macherey, Wolfgang</creatorcontrib><creatorcontrib>Schuster, Michael</creatorcontrib><creatorcontrib>Wu, Yonghui</creatorcontrib><creatorcontrib>Chen, Zhifeng</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hughes, Macduff Richard</au><au>Parmar, Niki J</au><au>Foster, George</au><au>Bapna, Ankur</au><au>Johnson Premkumar, Melvin Jose</au><au>Chen, Xu</au><au>Jones, Llion Owen</au><au>Firat, Orhan</au><au>Macherey, Wolfgang</au><au>Schuster, Michael</au><au>Wu, Yonghui</au><au>Chen, Zhifeng</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>MACHINE TRANSLATION USING NEURAL NETWORK MODELS</title><date>2020-01-30</date><risdate>2020</risdate><abstract>Methods, systems, and apparatus, including computer programs encoded on computer storage media, for machine translation using neural networks. In some implementations, a text in one language is translated into a second language using a neural network model. The model can include an encoder neural network comprising a plurality of bidirectional recurrent neural network layers. The encoding vectors are processed using a multi-headed attention module configured to generate multiple attention context vectors for each encoding vector. A decoder neural network generates a sequence of decoder output vectors using the attention context vectors. The decoder output vectors can represent distributions over various language elements of the second language, allowing a translation of the text into the second language to be determined based on the sequence of decoder output vectors.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2020034436A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
| title | MACHINE TRANSLATION USING NEURAL NETWORK MODELS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-31T04%3A56%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=Hughes,%20Macduff%20Richard&rft.date=2020-01-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2020034436A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |