Matches in SemOpenAlex for { <https://semopenalex.org/work/W2947394710> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2947394710 abstract "In this work, we introduce a novel algorithm for solving the textbook question answering (TQA) task which describes more realistic QA problems compared to other recent tasks. We mainly focus on two related issues with analysis of the TQA dataset. First, solving the TQA problems requires to comprehend multi-modal contexts in complicated input data. To tackle this issue of extracting knowledge features from long text lessons and merging them with visual features, we establish a context graph from texts and images, and propose a new module f-GCN based on graph convolutional networks (GCN). Second, scientific terms are not spread over the chapters and subjects are split in the TQA dataset. To overcome this so called out-of-domain issue, before learning QA problems, we introduce a novel self-supervised open-set learning process without any annotations. The experimental results show that our model significantly outperforms prior state-of-the-art methods. Moreover, ablation studies validate that both methods of incorporating f-GCN for extracting knowledge from multi-modal contexts and our newly proposed self-supervised learning process are effective for TQA problems." @default.
- W2947394710 created "2019-06-07" @default.
- W2947394710 creator A5061978920 @default.
- W2947394710 creator A5083561780 @default.
- W2947394710 creator A5084897975 @default.
- W2947394710 date "2018-11-01" @default.
- W2947394710 modified "2023-09-26" @default.
- W2947394710 title "Textbook Question Answering with Multi-modal Context Graph Understanding and Self-supervised Open-set Comprehension" @default.
- W2947394710 cites W2123442489 @default.
- W2947394710 cites W2125436846 @default.
- W2947394710 cites W2250539671 @default.
- W2947394710 cites W2307512708 @default.
- W2947394710 cites W2412400526 @default.
- W2947394710 cites W2427527485 @default.
- W2947394710 cites W2519887557 @default.
- W2947394710 cites W2561715562 @default.
- W2947394710 cites W2746097825 @default.
- W2947394710 cites W2799088654 @default.
- W2947394710 cites W2808877322 @default.
- W2947394710 cites W2951534261 @default.
- W2947394710 cites W2951815760 @default.
- W2947394710 cites W2962779575 @default.
- W2947394710 cites W2962959437 @default.
- W2947394710 cites W2963150162 @default.
- W2947394710 cites W2963532541 @default.
- W2947394710 cites W2963656855 @default.
- W2947394710 cites W2963668159 @default.
- W2947394710 cites W2963954913 @default.
- W2947394710 cites W2964321699 @default.
- W2947394710 doi "https://doi.org/10.48550/arxiv.1811.00232" @default.
- W2947394710 hasPublicationYear "2018" @default.
- W2947394710 type Work @default.
- W2947394710 sameAs 2947394710 @default.
- W2947394710 citedByCount "0" @default.
- W2947394710 crossrefType "posted-content" @default.
- W2947394710 hasAuthorship W2947394710A5061978920 @default.
- W2947394710 hasAuthorship W2947394710A5083561780 @default.
- W2947394710 hasAuthorship W2947394710A5084897975 @default.
- W2947394710 hasBestOaLocation W29473947101 @default.
- W2947394710 hasConcept C119857082 @default.
- W2947394710 hasConcept C132525143 @default.
- W2947394710 hasConcept C151730666 @default.
- W2947394710 hasConcept C154945302 @default.
- W2947394710 hasConcept C177264268 @default.
- W2947394710 hasConcept C185592680 @default.
- W2947394710 hasConcept C188027245 @default.
- W2947394710 hasConcept C199360897 @default.
- W2947394710 hasConcept C204321447 @default.
- W2947394710 hasConcept C2779343474 @default.
- W2947394710 hasConcept C41008148 @default.
- W2947394710 hasConcept C44291984 @default.
- W2947394710 hasConcept C71139939 @default.
- W2947394710 hasConcept C80444323 @default.
- W2947394710 hasConcept C86803240 @default.
- W2947394710 hasConceptScore W2947394710C119857082 @default.
- W2947394710 hasConceptScore W2947394710C132525143 @default.
- W2947394710 hasConceptScore W2947394710C151730666 @default.
- W2947394710 hasConceptScore W2947394710C154945302 @default.
- W2947394710 hasConceptScore W2947394710C177264268 @default.
- W2947394710 hasConceptScore W2947394710C185592680 @default.
- W2947394710 hasConceptScore W2947394710C188027245 @default.
- W2947394710 hasConceptScore W2947394710C199360897 @default.
- W2947394710 hasConceptScore W2947394710C204321447 @default.
- W2947394710 hasConceptScore W2947394710C2779343474 @default.
- W2947394710 hasConceptScore W2947394710C41008148 @default.
- W2947394710 hasConceptScore W2947394710C44291984 @default.
- W2947394710 hasConceptScore W2947394710C71139939 @default.
- W2947394710 hasConceptScore W2947394710C80444323 @default.
- W2947394710 hasConceptScore W2947394710C86803240 @default.
- W2947394710 hasLocation W29473947101 @default.
- W2947394710 hasOpenAccess W2947394710 @default.
- W2947394710 hasPrimaryLocation W29473947101 @default.
- W2947394710 hasRelatedWork W128392744 @default.
- W2947394710 hasRelatedWork W1483367581 @default.
- W2947394710 hasRelatedWork W1517743118 @default.
- W2947394710 hasRelatedWork W1518289136 @default.
- W2947394710 hasRelatedWork W1527340856 @default.
- W2947394710 hasRelatedWork W1560657467 @default.
- W2947394710 hasRelatedWork W207304934 @default.
- W2947394710 hasRelatedWork W2346333693 @default.
- W2947394710 hasRelatedWork W2747680751 @default.
- W2947394710 hasRelatedWork W61303690 @default.
- W2947394710 isParatext "false" @default.
- W2947394710 isRetracted "false" @default.
- W2947394710 magId "2947394710" @default.
- W2947394710 workType "article" @default.