Matches in SemOpenAlex for { <https://semopenalex.org/work/W2726413184> ?p ?o ?g. }
- W2726413184 abstract "In state-of-the-art Neural Machine Translation (NMT), an attention mechanism is used during decoding to enhance the translation. At every step, the decoder uses this mechanism to focus on different parts of the source sentence to gather the most useful information before outputting its target word. Recently, the effectiveness of the attention mechanism has also been explored for multi-modal tasks, where it becomes possible to focus both on sentence parts and image regions that they describe. In this paper, we compare several attention mechanism on the multi-modal translation task (English, image → German) and evaluate the ability of the model to make use of images to improve translation. We surpass state-of-the-art scores on the Multi30k data set, we nevertheless identify and report different misbehavior of the machine while translating." @default.
- W2726413184 created "2017-07-14" @default.
- W2726413184 creator A5005041960 @default.
- W2726413184 creator A5083563222 @default.
- W2726413184 date "2017-01-01" @default.
- W2726413184 modified "2023-10-17" @default.
- W2726413184 title "An empirical study on the effectiveness of images in Multimodal Neural Machine Translation" @default.
- W2726413184 cites W1514535095 @default.
- W2726413184 cites W1850742715 @default.
- W2726413184 cites W1902237438 @default.
- W2726413184 cites W1924770834 @default.
- W2726413184 cites W2101105183 @default.
- W2726413184 cites W2130942839 @default.
- W2726413184 cites W2133459682 @default.
- W2726413184 cites W2133564696 @default.
- W2726413184 cites W2149327368 @default.
- W2726413184 cites W2157331557 @default.
- W2726413184 cites W2194775991 @default.
- W2726413184 cites W2345720230 @default.
- W2726413184 cites W2417549359 @default.
- W2726413184 cites W2509282593 @default.
- W2726413184 cites W2513263213 @default.
- W2726413184 cites W2593341061 @default.
- W2726413184 cites W2594229957 @default.
- W2726413184 cites W2602344811 @default.
- W2726413184 cites W2949888546 @default.
- W2726413184 cites W2951527505 @default.
- W2726413184 cites W2962784628 @default.
- W2726413184 cites W2963069010 @default.
- W2726413184 cites W2963266340 @default.
- W2726413184 cites W2964036520 @default.
- W2726413184 cites W2964308564 @default.
- W2726413184 cites W2964335273 @default.
- W2726413184 cites W6908809 @default.
- W2726413184 doi "https://doi.org/10.18653/v1/d17-1095" @default.
- W2726413184 hasPublicationYear "2017" @default.
- W2726413184 type Work @default.
- W2726413184 sameAs 2726413184 @default.
- W2726413184 citedByCount "17" @default.
- W2726413184 countsByYear W27264131842017 @default.
- W2726413184 countsByYear W27264131842019 @default.
- W2726413184 countsByYear W27264131842020 @default.
- W2726413184 countsByYear W27264131842021 @default.
- W2726413184 countsByYear W27264131842022 @default.
- W2726413184 countsByYear W27264131842023 @default.
- W2726413184 crossrefType "proceedings-article" @default.
- W2726413184 hasAuthorship W2726413184A5005041960 @default.
- W2726413184 hasAuthorship W2726413184A5083563222 @default.
- W2726413184 hasBestOaLocation W27264131841 @default.
- W2726413184 hasConcept C104317684 @default.
- W2726413184 hasConcept C105580179 @default.
- W2726413184 hasConcept C111472728 @default.
- W2726413184 hasConcept C11413529 @default.
- W2726413184 hasConcept C115961682 @default.
- W2726413184 hasConcept C120665830 @default.
- W2726413184 hasConcept C121332964 @default.
- W2726413184 hasConcept C130597682 @default.
- W2726413184 hasConcept C138885662 @default.
- W2726413184 hasConcept C149364088 @default.
- W2726413184 hasConcept C154945302 @default.
- W2726413184 hasConcept C177264268 @default.
- W2726413184 hasConcept C185592680 @default.
- W2726413184 hasConcept C188027245 @default.
- W2726413184 hasConcept C192209626 @default.
- W2726413184 hasConcept C199360897 @default.
- W2726413184 hasConcept C203005215 @default.
- W2726413184 hasConcept C204321447 @default.
- W2726413184 hasConcept C24687705 @default.
- W2726413184 hasConcept C2777530160 @default.
- W2726413184 hasConcept C28490314 @default.
- W2726413184 hasConcept C41008148 @default.
- W2726413184 hasConcept C55493867 @default.
- W2726413184 hasConcept C57273362 @default.
- W2726413184 hasConcept C71139939 @default.
- W2726413184 hasConcept C89611455 @default.
- W2726413184 hasConceptScore W2726413184C104317684 @default.
- W2726413184 hasConceptScore W2726413184C105580179 @default.
- W2726413184 hasConceptScore W2726413184C111472728 @default.
- W2726413184 hasConceptScore W2726413184C11413529 @default.
- W2726413184 hasConceptScore W2726413184C115961682 @default.
- W2726413184 hasConceptScore W2726413184C120665830 @default.
- W2726413184 hasConceptScore W2726413184C121332964 @default.
- W2726413184 hasConceptScore W2726413184C130597682 @default.
- W2726413184 hasConceptScore W2726413184C138885662 @default.
- W2726413184 hasConceptScore W2726413184C149364088 @default.
- W2726413184 hasConceptScore W2726413184C154945302 @default.
- W2726413184 hasConceptScore W2726413184C177264268 @default.
- W2726413184 hasConceptScore W2726413184C185592680 @default.
- W2726413184 hasConceptScore W2726413184C188027245 @default.
- W2726413184 hasConceptScore W2726413184C192209626 @default.
- W2726413184 hasConceptScore W2726413184C199360897 @default.
- W2726413184 hasConceptScore W2726413184C203005215 @default.
- W2726413184 hasConceptScore W2726413184C204321447 @default.
- W2726413184 hasConceptScore W2726413184C24687705 @default.
- W2726413184 hasConceptScore W2726413184C2777530160 @default.
- W2726413184 hasConceptScore W2726413184C28490314 @default.
- W2726413184 hasConceptScore W2726413184C41008148 @default.
- W2726413184 hasConceptScore W2726413184C55493867 @default.
- W2726413184 hasConceptScore W2726413184C57273362 @default.
- W2726413184 hasConceptScore W2726413184C71139939 @default.