Challenge: Pre-trained models on document images with transformer-based backbones have led to significant performance gains in this field.
Approach: They propose a multi-modal pre-training model that combines text, layout and image . they propose to use local 1D position instead of global 1D positions as layout input .
Outcome: The proposed model can achieve state-of-the-art results on a wide variety of VrDU problems.

Similar Papers

LayoutLMv2: Multi-modal Pre-training for Visually-rich Document Understanding (2021.acl-long)

Copied to clipboard

Challenge: Existing pre-training tasks for text and layout are effective in visually-rich document understanding tasks.
Approach: They propose to combine pre-training tasks with a multi-modal model to model interaction between text, layout and image in a single multi-module framework.
Outcome: The proposed model outperforms LayoutLM by a large margin on visual-rich document understanding tasks.
Visually Guided Generative Text-Layout Pre-training for Document Intelligence (2024.naacl-long)

Copied to clipboard

Challenge: Prior work shows that pre-training techniques can boost the performance of visual document understanding (VDU) . Xu et al., 2020;; Gu e t al, 2021;; Appalaraju e al. 2022)
Approach: They propose a visually guided generative text-layout pre-training method that optimizes hierarchical language and layout modeling objectives to generate interleaved text and layout sequences.
Outcome: The proposed model can process word-intensive documents of any length and achieves competitive performance over baselines on VDU tasks.
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for visually rich document understanding lack layout-centered knowledge . experimental results show that ERNIE-Layout improves layout awareness .
Approach: They propose a document pre-training solution with layout knowledge enhancement in the whole workflow to learn better representations that combine the features from text, layout, and image.
Outcome: The proposed model outperforms existing models on key downstream tasks.
Semantics-enhanced Cross-modal Masked Image Modeling for Vision-Language Pre-training (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for vision-language pre-training lack high-level semantics and text is not sufficiently involved in masked modeling.
Approach: They propose a semantics-enhanced cross-modal MIM framework for vision-language representation learning that harvests high-level semantics from global image features via self-supervised agreement learning and transfers them to local patch encodings by sharing the encode space.
Outcome: The proposed model achieves state-of-the-art or competitive performance on multiple vision-language tasks.
Curriculum Masking in Vision-Language Pretraining to Maximize Cross Modal Interaction (2024.naacl-long)

Copied to clipboard

Challenge: masked language modeling is widely used as a pretraining component in Vision and language (V+L) but performance on benchmarks has not received the attention it deserves.
Approach: They propose a curriculum masking scheme that uses a parallel mask selection agent to mask tokens at a frequency proportional to the level of cross modal interaction necessary to reconstruct them.
Outcome: The proposed method improves relational understanding on a wide range of V+L tasks.
ReLayout: Towards Real-World Document Understanding via Layout-enhanced Pre-training (2025.coling-main)

Copied to clipboard

Challenge: Recent approaches for visually-rich document understanding use manually annotated semantic groups.
Approach: They propose a new variant of the VrDU task that does not use manually annotated semantic groups.
Outcome: The proposed method improves on the existing methods while sacrificing performance.
MarkupLM: Pre-training of Text and Markup Language for Visually Rich Document Understanding (2022.acl-long)

Copied to clipboard

Challenge: Existing layout-based pre-training approaches are not easy to apply to VRDU tasks.
Approach: They propose to use markup languages as the backbone for document understanding tasks where text and markup information are jointly pre-trained.
Outcome: The proposed model outperforms existing models on document understanding tasks.
LayoutLLM: Large Language Model Instruction Tuning for Visually Rich Document Understanding (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to enhance document comprehension require fine-tuning for each task and dataset, and are expensive to train and operate.
Approach: They propose a more flexible document analysis method that integrates visual-rich document understanding with large-scale language models (LLMs) by leveraging existing research in document image understanding and LLMs’ superior language understanding capabilities, the proposed model performs an understanding of document images in a single model.
Outcome: The proposed model improves on the baseline model in document image understanding tasks.
Visually-Enhanced Phrase Understanding (2023.findings-acl)

Copied to clipboard

Challenge: Large-scale vision-language pre-training models generate high-quality textual representations, which often outperform models that are purely text-based, such as BERT.
Approach: They propose to utilize both textual and visual encoders of multi-modal pre-trained models to enhance language understanding tasks by generating an image associated with a textual prompt.
Outcome: The proposed method outperforms models that are purely text-based on visual and textual understanding tasks and significantly improves the entity clustering task.
Learning Variational Word Masks to Improve the Interpretability of Neural Text Classifiers (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for improving model interpretability require prior information or human annotations as additional inputs.
Approach: They propose a variational word mask method to automatically learn task-specific important words and reduce irrelevant information on classification, which ultimately improves model interpretability.
Outcome: The proposed method improves model prediction accuracy and interpretability on seven datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations