ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909350992281600 |
|---|---|
| author | Jiang, Zhouqiang Wang, Bowen Chen, Junhao Nakashima, Yuta |
| author_facet | Jiang, Zhouqiang Wang, Bowen Chen, Junhao Nakashima, Yuta |
| contents | Recent approaches for visually-rich document understanding (VrDU) uses manually annotated semantic groups, where a semantic group encompasses all semantically relevant but not obviously grouped words. As OCR tools are unable to automatically identify such grouping, we argue that current VrDU approaches are unrealistic. We thus introduce a new variant of the VrDU task, real-world visually-rich document understanding (ReVrDU), that does not allow for using manually annotated semantic groups. We also propose a new method, ReLayout, compliant with the ReVrDU scenario, which learns to capture semantic grouping through arranging words and bringing the representations of words that belong to the potential same semantic group closer together. Our experimental results demonstrate the performance of existing methods is deteriorated with the ReVrDU task, while ReLayout shows superiour performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10471 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training Jiang, Zhouqiang Wang, Bowen Chen, Junhao Nakashima, Yuta Computer Vision and Pattern Recognition Recent approaches for visually-rich document understanding (VrDU) uses manually annotated semantic groups, where a semantic group encompasses all semantically relevant but not obviously grouped words. As OCR tools are unable to automatically identify such grouping, we argue that current VrDU approaches are unrealistic. We thus introduce a new variant of the VrDU task, real-world visually-rich document understanding (ReVrDU), that does not allow for using manually annotated semantic groups. We also propose a new method, ReLayout, compliant with the ReVrDU scenario, which learns to capture semantic grouping through arranging words and bringing the representations of words that belong to the potential same semantic group closer together. Our experimental results demonstrate the performance of existing methods is deteriorated with the ReVrDU task, while ReLayout shows superiour performance. |
| title | ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.10471 |