DocSynthv2: A Practical Autoregressive Modeling for Document Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Biswas, Sanket, Jain, Rajiv, Morariu, Vlad I., Gu, Jiuxiang, Mathur, Puneet, Wigington, Curtis, Sun, Tong, Lladós, Josep
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913388413583360
author Biswas, Sanket
Jain, Rajiv
Morariu, Vlad I.
Gu, Jiuxiang
Mathur, Puneet
Wigington, Curtis
Sun, Tong
Lladós, Josep
author_facet Biswas, Sanket
Jain, Rajiv
Morariu, Vlad I.
Gu, Jiuxiang
Mathur, Puneet
Wigington, Curtis
Sun, Tong
Lladós, Josep
contents While the generation of document layouts has been extensively explored, comprehensive document generation encompassing both layout and content presents a more complex challenge. This paper delves into this advanced domain, proposing a novel approach called DocSynthv2 through the development of a simple yet effective autoregressive structured model. Our model, distinct in its integration of both layout and textual cues, marks a step beyond existing layout-generation approaches. By focusing on the relationship between the structural elements and the textual content within documents, we aim to generate cohesive and contextually relevant documents without any reliance on visual components. Through experimental studies on our curated benchmark for the new task, we demonstrate the ability of our model combining layout and textual information in enhancing the generation quality and relevance of documents, opening new pathways for research in document creation and automated design. Our findings emphasize the effectiveness of autoregressive models in handling complex document generation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08354
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DocSynthv2: A Practical Autoregressive Modeling for Document Generation
Biswas, Sanket
Jain, Rajiv
Morariu, Vlad I.
Gu, Jiuxiang
Mathur, Puneet
Wigington, Curtis
Sun, Tong
Lladós, Josep
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
While the generation of document layouts has been extensively explored, comprehensive document generation encompassing both layout and content presents a more complex challenge. This paper delves into this advanced domain, proposing a novel approach called DocSynthv2 through the development of a simple yet effective autoregressive structured model. Our model, distinct in its integration of both layout and textual cues, marks a step beyond existing layout-generation approaches. By focusing on the relationship between the structural elements and the textual content within documents, we aim to generate cohesive and contextually relevant documents without any reliance on visual components. Through experimental studies on our curated benchmark for the new task, we demonstrate the ability of our model combining layout and textual information in enhancing the generation quality and relevance of documents, opening new pathways for research in document creation and automated design. Our findings emphasize the effectiveness of autoregressive models in handling complex document generation tasks.
title DocSynthv2: A Practical Autoregressive Modeling for Document Generation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2406.08354