Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042584649> ?p ?o ?g. }
- W3042584649 abstract "Multi-modal neural machine translation (NMT) aims to translate source sentences into a target language paired with images. However, dominant multi-modal NMT models do not fully exploit fine-grained semantic correspondences between semantic units of different modalities, which have potential to refine multi-modal representation learning. To deal with this issue, in this paper, we propose a novel graph-based multi-modal fusion encoder for NMT. Specifically, we first represent the input sentence and image using a unified multi-modal graph, which captures various semantic relationships between multi-modal semantic units (words and visual objects). We then stack multiple graph-based multi-modal fusion layers that iteratively perform semantic interactions to learn node representations. Finally, these representations provide an attention-based context vector for the decoder. We evaluate our proposed encoder on the Multi30K datasets. Experimental results and in-depth analysis show the superiority of our multi-modal NMT model." @default.
- W3042584649 created "2020-07-23" @default.
- W3042584649 creator A5024849044 @default.
- W3042584649 creator A5041174317 @default.
- W3042584649 creator A5050209478 @default.
- W3042584649 creator A5055469774 @default.
- W3042584649 creator A5056683457 @default.
- W3042584649 creator A5066326238 @default.
- W3042584649 creator A5083964406 @default.
- W3042584649 date "2020-07-17" @default.
- W3042584649 modified "2023-09-23" @default.
- W3042584649 title "A Novel Graph-based Multi-modal Fusion Encoder for Neural Machine Translation" @default.
- W3042584649 cites W1501856433 @default.
- W3042584649 cites W2101105183 @default.
- W3042584649 cites W2133459682 @default.
- W3042584649 cites W2513263213 @default.
- W3042584649 cites W2581101319 @default.
- W3042584649 cites W2593341061 @default.
- W3042584649 cites W2613718673 @default.
- W3042584649 cites W2772470221 @default.
- W3042584649 cites W2798749466 @default.
- W3042584649 cites W2808877322 @default.
- W3042584649 cites W2888070626 @default.
- W3042584649 cites W2889903020 @default.
- W3042584649 cites W2902031175 @default.
- W3042584649 cites W2903343986 @default.
- W3042584649 cites W2950207430 @default.
- W3042584649 cites W2950848235 @default.
- W3042584649 cites W2950886580 @default.
- W3042584649 cites W2950898568 @default.
- W3042584649 cites W2962779575 @default.
- W3042584649 cites W2962784628 @default.
- W3042584649 cites W2962964995 @default.
- W3042584649 cites W2963360627 @default.
- W3042584649 cites W2963403868 @default.
- W3042584649 cites W2963521239 @default.
- W3042584649 cites W2963532541 @default.
- W3042584649 cites W2963858333 @default.
- W3042584649 cites W2963988211 @default.
- W3042584649 cites W2964113829 @default.
- W3042584649 cites W2964192290 @default.
- W3042584649 cites W2964345214 @default.
- W3042584649 cites W2964400841 @default.
- W3042584649 cites W2964972381 @default.
- W3042584649 cites W2970231061 @default.
- W3042584649 cites W2987734933 @default.
- W3042584649 cites W3004349648 @default.
- W3042584649 doi "https://doi.org/10.48550/arxiv.2007.08742" @default.
- W3042584649 hasPublicationYear "2020" @default.
- W3042584649 type Work @default.
- W3042584649 sameAs 3042584649 @default.
- W3042584649 citedByCount "3" @default.
- W3042584649 countsByYear W30425846492020 @default.
- W3042584649 countsByYear W30425846492021 @default.
- W3042584649 crossrefType "posted-content" @default.
- W3042584649 hasAuthorship W3042584649A5024849044 @default.
- W3042584649 hasAuthorship W3042584649A5041174317 @default.
- W3042584649 hasAuthorship W3042584649A5050209478 @default.
- W3042584649 hasAuthorship W3042584649A5055469774 @default.
- W3042584649 hasAuthorship W3042584649A5056683457 @default.
- W3042584649 hasAuthorship W3042584649A5066326238 @default.
- W3042584649 hasAuthorship W3042584649A5083964406 @default.
- W3042584649 hasBestOaLocation W30425846491 @default.
- W3042584649 hasConcept C111919701 @default.
- W3042584649 hasConcept C118505674 @default.
- W3042584649 hasConcept C132525143 @default.
- W3042584649 hasConcept C153180895 @default.
- W3042584649 hasConcept C154945302 @default.
- W3042584649 hasConcept C165696696 @default.
- W3042584649 hasConcept C17744445 @default.
- W3042584649 hasConcept C179372163 @default.
- W3042584649 hasConcept C185592680 @default.
- W3042584649 hasConcept C188027245 @default.
- W3042584649 hasConcept C199539241 @default.
- W3042584649 hasConcept C203005215 @default.
- W3042584649 hasConcept C204321447 @default.
- W3042584649 hasConcept C205711294 @default.
- W3042584649 hasConcept C2776359362 @default.
- W3042584649 hasConcept C2777530160 @default.
- W3042584649 hasConcept C38652104 @default.
- W3042584649 hasConcept C41008148 @default.
- W3042584649 hasConcept C71139939 @default.
- W3042584649 hasConcept C80444323 @default.
- W3042584649 hasConcept C94625758 @default.
- W3042584649 hasConceptScore W3042584649C111919701 @default.
- W3042584649 hasConceptScore W3042584649C118505674 @default.
- W3042584649 hasConceptScore W3042584649C132525143 @default.
- W3042584649 hasConceptScore W3042584649C153180895 @default.
- W3042584649 hasConceptScore W3042584649C154945302 @default.
- W3042584649 hasConceptScore W3042584649C165696696 @default.
- W3042584649 hasConceptScore W3042584649C17744445 @default.
- W3042584649 hasConceptScore W3042584649C179372163 @default.
- W3042584649 hasConceptScore W3042584649C185592680 @default.
- W3042584649 hasConceptScore W3042584649C188027245 @default.
- W3042584649 hasConceptScore W3042584649C199539241 @default.
- W3042584649 hasConceptScore W3042584649C203005215 @default.
- W3042584649 hasConceptScore W3042584649C204321447 @default.
- W3042584649 hasConceptScore W3042584649C205711294 @default.
- W3042584649 hasConceptScore W3042584649C2776359362 @default.
- W3042584649 hasConceptScore W3042584649C2777530160 @default.