FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890907172> ?p ?o ?g. }

• W2890907172 abstract "Recent work has shown how to learn better visual-semantic embeddings by leveraging image descriptions in more than one language. Here, we investigate in detail which conditions affect the performance of this type of grounded language learning model. We show that multilingual training improves over bilingual training, and that low-resource languages benefit from training with higher-resource languages. We demonstrate that a multilingual model can be trained equally well on either translations or comparable sentence pairs, and that annotating the same set of images in multiple language enables further improvements via an additional caption-caption ranking objective." @default.
• W2890907172 created "2018-09-27" @default.
• W2890907172 creator A5010165733 @default.
• W2890907172 creator A5022698890 @default.
• W2890907172 creator A5029159426 @default.
• W2890907172 creator A5032540574 @default.
• W2890907172 creator A5047382001 @default.
• W2890907172 date "2018-01-01" @default.
• W2890907172 modified "2023-10-16" @default.
• W2890907172 title "Lessons Learned in Multilingual Grounded Language Learning" @default.
• W2890907172 cites W1514535095 @default.
• W2890907172 cites W1527575280 @default.
• W2890907172 cites W1895577753 @default.
• W2890907172 cites W1924770834 @default.
• W2890907172 cites W1933349210 @default.
• W2890907172 cites W1980776243 @default.
• W2890907172 cites W2067438047 @default.
• W2890907172 cites W2108598243 @default.
• W2890907172 cites W2112184938 @default.
• W2890907172 cites W2117865617 @default.
• W2890907172 cites W2126400076 @default.
• W2890907172 cites W2133458109 @default.
• W2890907172 cites W2145056192 @default.
• W2890907172 cites W2194775991 @default.
• W2890907172 cites W2250548009 @default.
• W2890907172 cites W2250676463 @default.
• W2890907172 cites W2250790822 @default.
• W2890907172 cites W2252200119 @default.
• W2890907172 cites W2291822808 @default.
• W2890907172 cites W2311921240 @default.
• W2890907172 cites W2345720230 @default.
• W2890907172 cites W2418300416 @default.
• W2890907172 cites W2471094925 @default.
• W2890907172 cites W2509282593 @default.
• W2890907172 cites W2509490957 @default.
• W2890907172 cites W2531207078 @default.
• W2890907172 cites W2566957588 @default.
• W2890907172 cites W2573834658 @default.
• W2890907172 cites W2583803255 @default.
• W2890907172 cites W2592831379 @default.
• W2890907172 cites W2739181657 @default.
• W2890907172 cites W2799615702 @default.
• W2890907172 cites W2917766698 @default.
• W2890907172 cites W2949999304 @default.
• W2890907172 cites W2962706528 @default.
• W2890907172 cites W2963088995 @default.
• W2890907172 cites W2963264012 @default.
• W2890907172 cites W2963324994 @default.
• W2890907172 cites W2963330681 @default.
• W2890907172 cites W2963383024 @default.
• W2890907172 cites W2963407669 @default.
• W2890907172 cites W2963496089 @default.
• W2890907172 cites W2963826397 @default.
• W2890907172 cites W2963899908 @default.
• W2890907172 cites W2963913768 @default.
• W2890907172 cites W2963988211 @default.
• W2890907172 cites W2964084097 @default.
• W2890907172 cites W2964121744 @default.
• W2890907172 doi "https://doi.org/10.18653/v1/k18-1039" @default.
• W2890907172 hasPublicationYear "2018" @default.
• W2890907172 type Work @default.
• W2890907172 sameAs 2890907172 @default.
• W2890907172 citedByCount "19" @default.
• W2890907172 countsByYear W28909071722018 @default.
• W2890907172 countsByYear W28909071722019 @default.
• W2890907172 countsByYear W28909071722020 @default.
• W2890907172 countsByYear W28909071722021 @default.
• W2890907172 countsByYear W28909071722022 @default.
• W2890907172 crossrefType "proceedings-article" @default.
• W2890907172 hasAuthorship W2890907172A5010165733 @default.
• W2890907172 hasAuthorship W2890907172A5022698890 @default.
• W2890907172 hasAuthorship W2890907172A5029159426 @default.
• W2890907172 hasAuthorship W2890907172A5032540574 @default.
• W2890907172 hasAuthorship W2890907172A5047382001 @default.
• W2890907172 hasBestOaLocation W28909071721 @default.
• W2890907172 hasConcept C154945302 @default.
• W2890907172 hasConcept C177264268 @default.
• W2890907172 hasConcept C189430467 @default.
• W2890907172 hasConcept C199360897 @default.
• W2890907172 hasConcept C204321447 @default.
• W2890907172 hasConcept C206345919 @default.
• W2890907172 hasConcept C2777530160 @default.
• W2890907172 hasConcept C31258907 @default.
• W2890907172 hasConcept C41008148 @default.
• W2890907172 hasConcept C51632099 @default.
• W2890907172 hasConceptScore W2890907172C154945302 @default.
• W2890907172 hasConceptScore W2890907172C177264268 @default.
• W2890907172 hasConceptScore W2890907172C189430467 @default.
• W2890907172 hasConceptScore W2890907172C199360897 @default.
• W2890907172 hasConceptScore W2890907172C204321447 @default.
• W2890907172 hasConceptScore W2890907172C206345919 @default.
• W2890907172 hasConceptScore W2890907172C2777530160 @default.
• W2890907172 hasConceptScore W2890907172C31258907 @default.
• W2890907172 hasConceptScore W2890907172C41008148 @default.
• W2890907172 hasConceptScore W2890907172C51632099 @default.
• W2890907172 hasLocation W28909071721 @default.
• W2890907172 hasLocation W28909071722 @default.
• W2890907172 hasLocation W28909071723 @default.
• W2890907172 hasOpenAccess W2890907172 @default.
• W2890907172 hasPrimaryLocation W28909071721 @default.

• next