M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training
We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2021-04 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Ni, Minheng Huang, Haoyang Lin, Su Cui, Edward Taroon Bharti Wang, Lijuan Gao, Jianfeng Zhang, Dongdong Duan, Nan |
| description | We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-switch strategy. Experiments are performed on the multilingual image retrieval task across two benchmark datasets, including MSCOCO and Multi30K. M3P can achieve comparable results for English and new state-of-the-art results for non-English languages. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2409768122</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2409768122</sourcerecordid><originalsourceid>FETCH-proquest_journals_24097681223</originalsourceid><addsrcrecordid>eNqNjMkKwjAURYMgWLT_EHBdSF866VYUFxZEdOOmBIySGtOal_T7jcMHuLrncocRiYDzNKkygAmJEVvGGBQl5DmPyLnm-yXdSWGNMjd6MmqQFoWmB9lbidI44VRnkA5K0Nprp5zA-5d0WPhQ_ZhHdwm4tzJxVqj32YyMr0KjjH86JfPN-rjaJr3tnl6ia9rOWxOiBjK2KIsqBeD_tV5SxUMn</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2409768122</pqid></control><display><type>article</type><title>M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training</title><source>Free E- Journals</source><creator>Ni, Minheng ; Huang, Haoyang ; Lin, Su ; Cui, Edward ; Taroon Bharti ; Wang, Lijuan ; Gao, Jianfeng ; Zhang, Dongdong ; Duan, Nan</creator><creatorcontrib>Ni, Minheng ; Huang, Haoyang ; Lin, Su ; Cui, Edward ; Taroon Bharti ; Wang, Lijuan ; Gao, Jianfeng ; Zhang, Dongdong ; Duan, Nan</creatorcontrib><description>We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-switch strategy. Experiments are performed on the multilingual image retrieval task across two benchmark datasets, including MSCOCO and Multi30K. M3P can achieve comparable results for English and new state-of-the-art results for non-English languages.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Learning ; Machine translation ; Multilingualism ; Natural language processing ; Representations ; Search engines ; Training</subject><ispartof>arXiv.org, 2021-04</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Ni, Minheng</creatorcontrib><creatorcontrib>Huang, Haoyang</creatorcontrib><creatorcontrib>Lin, Su</creatorcontrib><creatorcontrib>Cui, Edward</creatorcontrib><creatorcontrib>Taroon Bharti</creatorcontrib><creatorcontrib>Wang, Lijuan</creatorcontrib><creatorcontrib>Gao, Jianfeng</creatorcontrib><creatorcontrib>Zhang, Dongdong</creatorcontrib><creatorcontrib>Duan, Nan</creatorcontrib><title>M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training</title><title>arXiv.org</title><description>We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-switch strategy. Experiments are performed on the multilingual image retrieval task across two benchmark datasets, including MSCOCO and Multi30K. M3P can achieve comparable results for English and new state-of-the-art results for non-English languages.</description><subject>Learning</subject><subject>Machine translation</subject><subject>Multilingualism</subject><subject>Natural language processing</subject><subject>Representations</subject><subject>Search engines</subject><subject>Training</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNjMkKwjAURYMgWLT_EHBdSF866VYUFxZEdOOmBIySGtOal_T7jcMHuLrncocRiYDzNKkygAmJEVvGGBQl5DmPyLnm-yXdSWGNMjd6MmqQFoWmB9lbidI44VRnkA5K0Nprp5zA-5d0WPhQ_ZhHdwm4tzJxVqj32YyMr0KjjH86JfPN-rjaJr3tnl6ia9rOWxOiBjK2KIsqBeD_tV5SxUMn</recordid><startdate>20210401</startdate><enddate>20210401</enddate><creator>Ni, Minheng</creator><creator>Huang, Haoyang</creator><creator>Lin, Su</creator><creator>Cui, Edward</creator><creator>Taroon Bharti</creator><creator>Wang, Lijuan</creator><creator>Gao, Jianfeng</creator><creator>Zhang, Dongdong</creator><creator>Duan, Nan</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</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>20210401</creationdate><title>M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training</title><author>Ni, Minheng ; Huang, Haoyang ; Lin, Su ; Cui, Edward ; Taroon Bharti ; Wang, Lijuan ; Gao, Jianfeng ; Zhang, Dongdong ; Duan, Nan</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24097681223</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Learning</topic><topic>Machine translation</topic><topic>Multilingualism</topic><topic>Natural language processing</topic><topic>Representations</topic><topic>Search engines</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Ni, Minheng</creatorcontrib><creatorcontrib>Huang, Haoyang</creatorcontrib><creatorcontrib>Lin, Su</creatorcontrib><creatorcontrib>Cui, Edward</creatorcontrib><creatorcontrib>Taroon Bharti</creatorcontrib><creatorcontrib>Wang, Lijuan</creatorcontrib><creatorcontrib>Gao, Jianfeng</creatorcontrib><creatorcontrib>Zhang, Dongdong</creatorcontrib><creatorcontrib>Duan, Nan</creatorcontrib><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 Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Ni, Minheng</au><au>Huang, Haoyang</au><au>Lin, Su</au><au>Cui, Edward</au><au>Taroon Bharti</au><au>Wang, Lijuan</au><au>Gao, Jianfeng</au><au>Zhang, Dongdong</au><au>Duan, Nan</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training</atitle><jtitle>arXiv.org</jtitle><date>2021-04-01</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>We present M3P, a Multitask Multilingual Multimodal Pre-trained model that combines multilingual pre-training and multimodal pre-training into a unified framework via multitask pre-training. Our goal is to learn universal representations that can map objects occurred in different modalities or texts expressed in different languages into a common semantic space. In addition, to explicitly encourage fine-grained alignment between images and non-English languages, we also propose Multimodal Code-switched Training (MCT) to combine monolingual pre-training and multimodal pre-training via a code-switch strategy. Experiments are performed on the multilingual image retrieval task across two benchmark datasets, including MSCOCO and Multi30K. M3P can achieve comparable results for English and new state-of-the-art results for non-English languages.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2021-04 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2409768122 |
| source | Free E- Journals |
| subjects | Learning Machine translation Multilingualism Natural language processing Representations Search engines Training |
| title | M3P: Learning Universal Representations via Multitask Multilingual Multimodal Pre-training |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T03%3A45%3A51IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=M3P:%20Learning%20Universal%20Representations%20via%20Multitask%20Multilingual%20Multimodal%20Pre-training&rft.jtitle=arXiv.org&rft.au=Ni,%20Minheng&rft.date=2021-04-01&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2409768122%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2409768122&rft_id=info:pmid/&rfr_iscdi=true |