Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304098606> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W4304098606 abstract "This paper focuses on solving Document Information Extraction (DIE) in the wild problem, which is rarely explored before. In contrast to existing studies mainly tailored for document cases in known templates with predefined layouts and keys under the ideal input without OCR errors involved, we aim to build up a more practical DIE paradigm for real-world scenarios where input document images may contain unknown layouts and keys in the scenes of the problematic OCR results. To achieve this goal, we propose a novel architecture, termed Query-driven Generative Network (QGN), which is equipped with two consecutive modules, i.e., Layout Context-aware Module (LCM) and Structured Generation Module (SGM). Given a document image with unseen layouts and fields, the former LCM yields the value prefix candidates serving as the query prompts for the SGM to generate the final key-value pairs even with OCR noise. To further investigate the potential of our method, we create a new large-scale dataset, named LArge-scale STructured Documents (LastDoc4000), containing 4,000 documents with 1,511 layouts and 3,500 different keys. In experiments, we demonstrate that our QGN consistently achieves the best F1-score on the new LastDoc4000 dataset by at most 30.32% absolute improvement. A more comprehensive experimental analysis and experiments on other public benchmarks also verify the effectiveness and robustness of our proposed method for the wild DIE task." @default.
- W4304098606 created "2022-10-10" @default.
- W4304098606 creator A5006572116 @default.
- W4304098606 creator A5016912950 @default.
- W4304098606 creator A5020994192 @default.
- W4304098606 creator A5022526821 @default.
- W4304098606 creator A5024986567 @default.
- W4304098606 creator A5063859253 @default.
- W4304098606 creator A5073750509 @default.
- W4304098606 creator A5084063805 @default.
- W4304098606 creator A5088664989 @default.
- W4304098606 date "2022-10-10" @default.
- W4304098606 modified "2023-10-16" @default.
- W4304098606 title "Query-driven Generative Network for Document Information Extraction in the Wild" @default.
- W4304098606 cites W1963728304 @default.
- W4304098606 cites W2144876877 @default.
- W4304098606 cites W2194187530 @default.
- W4304098606 cites W2965512000 @default.
- W4304098606 cites W3034864438 @default.
- W4304098606 cites W3092515419 @default.
- W4304098606 cites W3092968218 @default.
- W4304098606 cites W3132296545 @default.
- W4304098606 cites W3171975879 @default.
- W4304098606 cites W3173306993 @default.
- W4304098606 cites W3173325518 @default.
- W4304098606 cites W3173777717 @default.
- W4304098606 cites W3176851559 @default.
- W4304098606 cites W3190292546 @default.
- W4304098606 cites W3190448953 @default.
- W4304098606 cites W3198609383 @default.
- W4304098606 cites W3202839357 @default.
- W4304098606 cites W4287854430 @default.
- W4304098606 doi "https://doi.org/10.1145/3503161.3547877" @default.
- W4304098606 hasPublicationYear "2022" @default.
- W4304098606 type Work @default.
- W4304098606 citedByCount "4" @default.
- W4304098606 countsByYear W43040986062023 @default.
- W4304098606 crossrefType "proceedings-article" @default.
- W4304098606 hasAuthorship W4304098606A5006572116 @default.
- W4304098606 hasAuthorship W4304098606A5016912950 @default.
- W4304098606 hasAuthorship W4304098606A5020994192 @default.
- W4304098606 hasAuthorship W4304098606A5022526821 @default.
- W4304098606 hasAuthorship W4304098606A5024986567 @default.
- W4304098606 hasAuthorship W4304098606A5063859253 @default.
- W4304098606 hasAuthorship W4304098606A5073750509 @default.
- W4304098606 hasAuthorship W4304098606A5084063805 @default.
- W4304098606 hasAuthorship W4304098606A5088664989 @default.
- W4304098606 hasConcept C104317684 @default.
- W4304098606 hasConcept C115961682 @default.
- W4304098606 hasConcept C124101348 @default.
- W4304098606 hasConcept C151730666 @default.
- W4304098606 hasConcept C154945302 @default.
- W4304098606 hasConcept C185592680 @default.
- W4304098606 hasConcept C23123220 @default.
- W4304098606 hasConcept C2779343474 @default.
- W4304098606 hasConcept C41008148 @default.
- W4304098606 hasConcept C55493867 @default.
- W4304098606 hasConcept C63479239 @default.
- W4304098606 hasConcept C86803240 @default.
- W4304098606 hasConcept C99498987 @default.
- W4304098606 hasConceptScore W4304098606C104317684 @default.
- W4304098606 hasConceptScore W4304098606C115961682 @default.
- W4304098606 hasConceptScore W4304098606C124101348 @default.
- W4304098606 hasConceptScore W4304098606C151730666 @default.
- W4304098606 hasConceptScore W4304098606C154945302 @default.
- W4304098606 hasConceptScore W4304098606C185592680 @default.
- W4304098606 hasConceptScore W4304098606C23123220 @default.
- W4304098606 hasConceptScore W4304098606C2779343474 @default.
- W4304098606 hasConceptScore W4304098606C41008148 @default.
- W4304098606 hasConceptScore W4304098606C55493867 @default.
- W4304098606 hasConceptScore W4304098606C63479239 @default.
- W4304098606 hasConceptScore W4304098606C86803240 @default.
- W4304098606 hasConceptScore W4304098606C99498987 @default.
- W4304098606 hasLocation W43040986061 @default.
- W4304098606 hasOpenAccess W4304098606 @default.
- W4304098606 hasPrimaryLocation W43040986061 @default.
- W4304098606 hasRelatedWork W1532073221 @default.
- W4304098606 hasRelatedWork W2049632933 @default.
- W4304098606 hasRelatedWork W2107220315 @default.
- W4304098606 hasRelatedWork W2171975302 @default.
- W4304098606 hasRelatedWork W2377538627 @default.
- W4304098606 hasRelatedWork W2729046585 @default.
- W4304098606 hasRelatedWork W2770593030 @default.
- W4304098606 hasRelatedWork W3154990682 @default.
- W4304098606 hasRelatedWork W4281727072 @default.
- W4304098606 hasRelatedWork W4312219546 @default.
- W4304098606 isParatext "false" @default.
- W4304098606 isRetracted "false" @default.
- W4304098606 workType "article" @default.