Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385890273> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W4385890273 abstract "In recent years, the use of multi-modal pre-trained Transformers has led to significant advancements in visually-rich document understanding. However, existing models have mainly focused on features such as text and vision while neglecting the importance of layout relationship between text nodes. In this paper, we propose GraphLayoutLM, a novel document understanding model that leverages the modeling of layout structure graph to inject document layout knowledge into the model. GraphLayoutLM utilizes a graph reordering algorithm to adjust the text sequence based on the graph structure. Additionally, our model uses a layout-aware multi-head self-attention layer to learn document layout knowledge. The proposed model enables the understanding of the spatial arrangement of text elements, improving document comprehension. We evaluate our model on various benchmarks, including FUNSD, XFUND and CORD, and achieve state-of-the-art results among these datasets. Our experimental results demonstrate that our proposed method provides a significant improvement over existing approaches and showcases the importance of incorporating layout information into document understanding models. We also conduct an ablation study to investigate the contribution of each component of our model. The results show that both the graph reordering algorithm and the layout-aware multi-head self-attention layer play a crucial role in achieving the best performance." @default.
- W4385890273 created "2023-08-17" @default.
- W4385890273 creator A5002584135 @default.
- W4385890273 creator A5003753939 @default.
- W4385890273 creator A5020073475 @default.
- W4385890273 creator A5036050911 @default.
- W4385890273 creator A5071287470 @default.
- W4385890273 date "2023-08-15" @default.
- W4385890273 modified "2023-09-27" @default.
- W4385890273 title "Enhancing Visually-Rich Document Understanding via Layout Structure Modeling" @default.
- W4385890273 doi "https://doi.org/10.48550/arxiv.2308.07777" @default.
- W4385890273 hasPublicationYear "2023" @default.
- W4385890273 type Work @default.
- W4385890273 citedByCount "0" @default.
- W4385890273 crossrefType "posted-content" @default.
- W4385890273 hasAuthorship W4385890273A5002584135 @default.
- W4385890273 hasAuthorship W4385890273A5003753939 @default.
- W4385890273 hasAuthorship W4385890273A5020073475 @default.
- W4385890273 hasAuthorship W4385890273A5036050911 @default.
- W4385890273 hasAuthorship W4385890273A5071287470 @default.
- W4385890273 hasBestOaLocation W43858902731 @default.
- W4385890273 hasConcept C112953755 @default.
- W4385890273 hasConcept C115961682 @default.
- W4385890273 hasConcept C132525143 @default.
- W4385890273 hasConcept C154945302 @default.
- W4385890273 hasConcept C23123220 @default.
- W4385890273 hasConcept C2911174283 @default.
- W4385890273 hasConcept C41008148 @default.
- W4385890273 hasConcept C72773152 @default.
- W4385890273 hasConcept C80444323 @default.
- W4385890273 hasConceptScore W4385890273C112953755 @default.
- W4385890273 hasConceptScore W4385890273C115961682 @default.
- W4385890273 hasConceptScore W4385890273C132525143 @default.
- W4385890273 hasConceptScore W4385890273C154945302 @default.
- W4385890273 hasConceptScore W4385890273C23123220 @default.
- W4385890273 hasConceptScore W4385890273C2911174283 @default.
- W4385890273 hasConceptScore W4385890273C41008148 @default.
- W4385890273 hasConceptScore W4385890273C72773152 @default.
- W4385890273 hasConceptScore W4385890273C80444323 @default.
- W4385890273 hasLocation W43858902731 @default.
- W4385890273 hasOpenAccess W4385890273 @default.
- W4385890273 hasPrimaryLocation W43858902731 @default.
- W4385890273 hasRelatedWork W1536405386 @default.
- W4385890273 hasRelatedWork W1597238586 @default.
- W4385890273 hasRelatedWork W2086064646 @default.
- W4385890273 hasRelatedWork W2115485936 @default.
- W4385890273 hasRelatedWork W2119135658 @default.
- W4385890273 hasRelatedWork W2326857978 @default.
- W4385890273 hasRelatedWork W2349174110 @default.
- W4385890273 hasRelatedWork W2357241418 @default.
- W4385890273 hasRelatedWork W2792377126 @default.
- W4385890273 hasRelatedWork W3022131925 @default.
- W4385890273 isParatext "false" @default.
- W4385890273 isRetracted "false" @default.
- W4385890273 workType "article" @default.