Matches in SemOpenAlex for { <https://semopenalex.org/work/W3129547686> ?p ?o ?g. }
- W3129547686 abstract "The task of graph-to-text generation aims at producing sentences that preserve the meaning of input graphs. As a crucial defect, the current state-of-the-art models may mess up or even drop the core structural information of input graphs when generating outputs. We propose to tackle this problem by leveraging richer training signals that can guide our model for preserving input information. In particular, we introduce two types of autoencoding losses, each individually focusing on different aspects (a.k.a. views) of input graphs. The losses are then back-propagated to better calibrate our model via multi-task training. Experiments on two benchmarks for graph-to-text generation show the effectiveness of our approach over a state-of-the-art baseline. Our code is available at url{http://github.com/Soistesimmer/AMR-multiview}." @default.
- W3129547686 created "2021-03-01" @default.
- W3129547686 creator A5010776860 @default.
- W3129547686 creator A5016877422 @default.
- W3129547686 creator A5034476404 @default.
- W3129547686 creator A5043893150 @default.
- W3129547686 creator A5066326238 @default.
- W3129547686 creator A5087988578 @default.
- W3129547686 creator A5088216458 @default.
- W3129547686 date "2021-02-12" @default.
- W3129547686 modified "2023-09-25" @default.
- W3129547686 title "Structural Information Preserving for Graph-to-Text Generation" @default.
- W3129547686 cites W1522301498 @default.
- W3129547686 cites W2064675550 @default.
- W3129547686 cites W2101105183 @default.
- W3129547686 cites W2133459682 @default.
- W3129547686 cites W2154579312 @default.
- W3129547686 cites W2157331557 @default.
- W3129547686 cites W2251071803 @default.
- W3129547686 cites W2252123671 @default.
- W3129547686 cites W2470862100 @default.
- W3129547686 cites W2739046565 @default.
- W3129547686 cites W2739894144 @default.
- W3129547686 cites W2758846169 @default.
- W3129547686 cites W2786660442 @default.
- W3129547686 cites W2798552002 @default.
- W3129547686 cites W2798749466 @default.
- W3129547686 cites W2889404673 @default.
- W3129547686 cites W2889874042 @default.
- W3129547686 cites W2890585661 @default.
- W3129547686 cites W2890996951 @default.
- W3129547686 cites W2924961378 @default.
- W3129547686 cites W2931198394 @default.
- W3129547686 cites W2932864487 @default.
- W3129547686 cites W2942179040 @default.
- W3129547686 cites W2949413855 @default.
- W3129547686 cites W2950898568 @default.
- W3129547686 cites W2951309718 @default.
- W3129547686 cites W2962676330 @default.
- W3129547686 cites W2962729880 @default.
- W3129547686 cites W2962784628 @default.
- W3129547686 cites W2962950136 @default.
- W3129547686 cites W2963201387 @default.
- W3129547686 cites W2963391817 @default.
- W3129547686 cites W2963403868 @default.
- W3129547686 cites W2963551569 @default.
- W3129547686 cites W2963571341 @default.
- W3129547686 cites W2963648186 @default.
- W3129547686 cites W2963706742 @default.
- W3129547686 cites W2963858333 @default.
- W3129547686 cites W2964116568 @default.
- W3129547686 cites W2964271186 @default.
- W3129547686 cites W2971087717 @default.
- W3129547686 cites W2971187756 @default.
- W3129547686 cites W2982951928 @default.
- W3129547686 cites W2996176596 @default.
- W3129547686 cites W2998702685 @default.
- W3129547686 cites W3003446182 @default.
- W3129547686 cites W3034731179 @default.
- W3129547686 cites W3099405210 @default.
- W3129547686 cites W81000870 @default.
- W3129547686 doi "https://doi.org/10.48550/arxiv.2102.06749" @default.
- W3129547686 hasPublicationYear "2021" @default.
- W3129547686 type Work @default.
- W3129547686 sameAs 3129547686 @default.
- W3129547686 citedByCount "0" @default.
- W3129547686 crossrefType "posted-content" @default.
- W3129547686 hasAuthorship W3129547686A5010776860 @default.
- W3129547686 hasAuthorship W3129547686A5016877422 @default.
- W3129547686 hasAuthorship W3129547686A5034476404 @default.
- W3129547686 hasAuthorship W3129547686A5043893150 @default.
- W3129547686 hasAuthorship W3129547686A5066326238 @default.
- W3129547686 hasAuthorship W3129547686A5087988578 @default.
- W3129547686 hasAuthorship W3129547686A5088216458 @default.
- W3129547686 hasBestOaLocation W31295476861 @default.
- W3129547686 hasConcept C111368507 @default.
- W3129547686 hasConcept C12725497 @default.
- W3129547686 hasConcept C127313418 @default.
- W3129547686 hasConcept C132525143 @default.
- W3129547686 hasConcept C154945302 @default.
- W3129547686 hasConcept C15744967 @default.
- W3129547686 hasConcept C162324750 @default.
- W3129547686 hasConcept C177264268 @default.
- W3129547686 hasConcept C187736073 @default.
- W3129547686 hasConcept C199360897 @default.
- W3129547686 hasConcept C204321447 @default.
- W3129547686 hasConcept C23123220 @default.
- W3129547686 hasConcept C2776760102 @default.
- W3129547686 hasConcept C2780451532 @default.
- W3129547686 hasConcept C2780876879 @default.
- W3129547686 hasConcept C2985684807 @default.
- W3129547686 hasConcept C41008148 @default.
- W3129547686 hasConcept C43126263 @default.
- W3129547686 hasConcept C542102704 @default.
- W3129547686 hasConcept C80444323 @default.
- W3129547686 hasConceptScore W3129547686C111368507 @default.
- W3129547686 hasConceptScore W3129547686C12725497 @default.
- W3129547686 hasConceptScore W3129547686C127313418 @default.
- W3129547686 hasConceptScore W3129547686C132525143 @default.
- W3129547686 hasConceptScore W3129547686C154945302 @default.