NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning
We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via...
Gespeichert in:
| Veröffentlicht in: | Prague bulletin of mathematical linguistics 2018-10, Vol.111 (1), p.113-124 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 124 |
|---|---|
| container_issue | 1 |
| container_start_page | 113 |
| container_title | Prague bulletin of mathematical linguistics |
| container_volume | 111 |
| creator | Peris, Álvaro Casacuberta, Francisco |
| description | We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning. NMT-Keras is based on an extended version of the popular Keras library, and it runs on Theano and TensorFlow. State-of-the-art neural machine translation models are deployed and used following the high-level framework provided by Keras. Given its high modularity and flexibility, it also has been extended to tackle different problems, such as image and video captioning, sentence classification and visual question answering. |
| doi_str_mv | 10.2478/pralin-2018-0010 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2167897793</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2167897793</sourcerecordid><originalsourceid>FETCH-LOGICAL-c2143-83f4775e6eac549f62d1827bcfedb2acfc906a33b18b85795fb74478cf6880f63</originalsourceid><addsrcrecordid>eNp1kL1PwzAQxS0EEqWwM1piDvgjsR0WhCpaKgpdSlfLceySEpxiJ5T-97gECRZuuZPufu_pHgDnGF2SlIurjVd15RKCsEgQwugADLBAaYJSRg7_zMfgJIQ1QkxQhgdg-fS4SB6MV-EaKrg0fgfHtfmsitrARdPUr1ULt1X7EpfjRncBNg5OXRsB3VYfBkYcKlfCuYvuBs6M8q5yq1NwZFUdzNlPH4Ln8d1idJ_M5pPp6HaWaIJTmghqU84zw4zSWZpbRkosCC-0NWVBlLY6R0xRWmBRiIznmS14Gr_VlgmBLKNDcNHrbnzz3pnQynXTeRctJcGMi5zznMYr1F9p34TgjZUbX70pv5MYyX16sk9P7tOT-_QictMjW1XHb0uz8t0uDr_6_6H4uyj9Agyvd1U</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2167897793</pqid></control><display><type>article</type><title>NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Peris, Álvaro ; Casacuberta, Francisco</creator><creatorcontrib>Peris, Álvaro ; Casacuberta, Francisco</creatorcontrib><description>We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning. NMT-Keras is based on an extended version of the popular Keras library, and it runs on Theano and TensorFlow. State-of-the-art neural machine translation models are deployed and used following the high-level framework provided by Keras. Given its high modularity and flexibility, it also has been extended to tackle different problems, such as image and video captioning, sentence classification and visual question answering.</description><identifier>ISSN: 1804-0462</identifier><identifier>ISSN: 0032-6585</identifier><identifier>EISSN: 1804-0462</identifier><identifier>DOI: 10.2478/pralin-2018-0010</identifier><language>eng</language><publisher>Prague: Sciendo</publisher><subject>Computational linguistics ; Deep learning ; Distance learning ; Image classification ; Interactive systems ; Machine learning ; Machine translation ; Modularity ; State of the art ; Video data</subject><ispartof>Prague bulletin of mathematical linguistics, 2018-10, Vol.111 (1), p.113-124</ispartof><rights>2018. This work is published under http://creativecommons.org/licenses/by-nc-nd/3.0 (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c2143-83f4775e6eac549f62d1827bcfedb2acfc906a33b18b85795fb74478cf6880f63</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,778,782,27907,27908</link.rule.ids></links><search><creatorcontrib>Peris, Álvaro</creatorcontrib><creatorcontrib>Casacuberta, Francisco</creatorcontrib><title>NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning</title><title>Prague bulletin of mathematical linguistics</title><description>We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning. NMT-Keras is based on an extended version of the popular Keras library, and it runs on Theano and TensorFlow. State-of-the-art neural machine translation models are deployed and used following the high-level framework provided by Keras. Given its high modularity and flexibility, it also has been extended to tackle different problems, such as image and video captioning, sentence classification and visual question answering.</description><subject>Computational linguistics</subject><subject>Deep learning</subject><subject>Distance learning</subject><subject>Image classification</subject><subject>Interactive systems</subject><subject>Machine learning</subject><subject>Machine translation</subject><subject>Modularity</subject><subject>State of the art</subject><subject>Video data</subject><issn>1804-0462</issn><issn>0032-6585</issn><issn>1804-0462</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AIMQZ</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNp1kL1PwzAQxS0EEqWwM1piDvgjsR0WhCpaKgpdSlfLceySEpxiJ5T-97gECRZuuZPufu_pHgDnGF2SlIurjVd15RKCsEgQwugADLBAaYJSRg7_zMfgJIQ1QkxQhgdg-fS4SB6MV-EaKrg0fgfHtfmsitrARdPUr1ULt1X7EpfjRncBNg5OXRsB3VYfBkYcKlfCuYvuBs6M8q5yq1NwZFUdzNlPH4Ln8d1idJ_M5pPp6HaWaIJTmghqU84zw4zSWZpbRkosCC-0NWVBlLY6R0xRWmBRiIznmS14Gr_VlgmBLKNDcNHrbnzz3pnQynXTeRctJcGMi5zznMYr1F9p34TgjZUbX70pv5MYyX16sk9P7tOT-_QictMjW1XHb0uz8t0uDr_6_6H4uyj9Agyvd1U</recordid><startdate>20181001</startdate><enddate>20181001</enddate><creator>Peris, Álvaro</creator><creator>Casacuberta, Francisco</creator><general>Sciendo</general><general>Institute of Formal and Applied Linguistics</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7T9</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AIMQZ</scope><scope>ALSLI</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>BYOGL</scope><scope>CCPQU</scope><scope>CPGLG</scope><scope>CRLPW</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>LIQON</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20181001</creationdate><title>NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning</title><author>Peris, Álvaro ; Casacuberta, Francisco</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c2143-83f4775e6eac549f62d1827bcfedb2acfc906a33b18b85795fb74478cf6880f63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Computational linguistics</topic><topic>Deep learning</topic><topic>Distance learning</topic><topic>Image classification</topic><topic>Interactive systems</topic><topic>Machine learning</topic><topic>Machine translation</topic><topic>Modularity</topic><topic>State of the art</topic><topic>Video data</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Peris, Álvaro</creatorcontrib><creatorcontrib>Casacuberta, Francisco</creatorcontrib><collection>CrossRef</collection><collection>Linguistics and Language Behavior Abstracts (LLBA)</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest One Literature</collection><collection>Social Science Premium Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>East Europe, Central Europe Database</collection><collection>ProQuest One Community College</collection><collection>Linguistics Collection</collection><collection>Linguistics Database</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>ProQuest One Literature - U.S. Customers Only</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><jtitle>Prague bulletin of mathematical linguistics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Peris, Álvaro</au><au>Casacuberta, Francisco</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning</atitle><jtitle>Prague bulletin of mathematical linguistics</jtitle><date>2018-10-01</date><risdate>2018</risdate><volume>111</volume><issue>1</issue><spage>113</spage><epage>124</epage><pages>113-124</pages><issn>1804-0462</issn><issn>0032-6585</issn><eissn>1804-0462</eissn><abstract>We present NMT-Keras, a flexible toolkit for training deep learning models, which puts a particular emphasis on the development of advanced applications of neural machine translation systems, such as interactive-predictive translation protocols and long-term adaptation of the translation system via continuous learning. NMT-Keras is based on an extended version of the popular Keras library, and it runs on Theano and TensorFlow. State-of-the-art neural machine translation models are deployed and used following the high-level framework provided by Keras. Given its high modularity and flexibility, it also has been extended to tackle different problems, such as image and video captioning, sentence classification and visual question answering.</abstract><cop>Prague</cop><pub>Sciendo</pub><doi>10.2478/pralin-2018-0010</doi><tpages>12</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1804-0462 |
| ispartof | Prague bulletin of mathematical linguistics, 2018-10, Vol.111 (1), p.113-124 |
| issn | 1804-0462 0032-6585 1804-0462 |
| language | eng |
| recordid | cdi_proquest_journals_2167897793 |
| source | Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Computational linguistics Deep learning Distance learning Image classification Interactive systems Machine learning Machine translation Modularity State of the art Video data |
| title | NMT-Keras: a Very Flexible Toolkit with a Focus on Interactive NMT and Online Learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T16%3A09%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=NMT-Keras:%20a%20Very%20Flexible%20Toolkit%20with%20a%20Focus%20on%20Interactive%20NMT%20and%20Online%20Learning&rft.jtitle=Prague%20bulletin%20of%20mathematical%20linguistics&rft.au=Peris,%20%C3%81lvaro&rft.date=2018-10-01&rft.volume=111&rft.issue=1&rft.spage=113&rft.epage=124&rft.pages=113-124&rft.issn=1804-0462&rft.eissn=1804-0462&rft_id=info:doi/10.2478/pralin-2018-0010&rft_dat=%3Cproquest_cross%3E2167897793%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2167897793&rft_id=info:pmid/&rfr_iscdi=true |