Related papers: Layout-Aware OCR for Black Digital Archives with U…
Document parsing is now widely used in applications, such as large-scale document digitization, retrieval-augmented generation, and domain-specific pipelines in healthcare and education. Benchmarking these models is crucial for assessing…
Visual Document Understanding (VDU) systems have achieved strong performance in information extraction by integrating textual, layout, and visual signals. However, their robustness under realistic adversarial perturbations remains…
We present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language models, whereas in the supervised setting, three different neural…
Large Multimodal Models (LMMs) have demonstrated impressive performance in recognizing document images with natural language instructions. However, it remains unclear to what extent capabilities in literacy with rich structure and…
Optical Character Recognition (OCR) for low-resource languages remains a significant challenge due to the scarcity of large-scale annotated training datasets. Languages such as Kashmiri, with approximately 7 million speakers and a complex…
Many real-world applications involve the use of Optical Character Recognition (OCR) engines to transform handwritten images into transcripts on which downstream Natural Language Processing (NLP) models are applied. In this process, OCR…
Companies regularly spend millions of dollars producing electronically-stored documents in legal matters. Recently, parties on both sides of the 'legal aisle' are accepting the use of machine learning techniques like text classification to…
Reading order detection is the cornerstone to understanding visually-rich documents (e.g., receipts and forms). Unfortunately, no existing work took advantage of advanced deep learning models because it is too laborious to annotate a large…
Historical documents frequently suffer from damage and inconsistencies, including missing or illegible text resulting from issues such as holes, ink problems, and storage damage. These missing portions or gaps are referred to as lacunae. In…
Page layout analysis is a fundamental step in document processing which enables to segment a page into regions of interest. With highly complex layouts and mixed scripts, scholarly commentaries are text-heavy documents which remain…
Since the dawn of the computing era, information has been represented digitally so that it can be processed by electronic computers. Paper books and documents were abundant and widely being published at that time; and hence, there was a…
Automating the annotation of scanned documents is challenging, requiring a balance between computational efficiency and accuracy. DocParseNet addresses this by combining deep learning and multi-modal learning to process both text and visual…
Information extraction (IE) from unstructured documents remains a critical challenge in data processing pipelines. Traditional optical character recognition (OCR) methods and conventional parsing engines demonstrate limited effectiveness…
Identifying high-quality webpages is fundamental for real-world search engines, which can fulfil users' information need with the less cognitive burden. Early studies of \emph{webpage quality assessment} usually design hand-crafted features…
A well-designed document communicates not only through its words but also through its visual eloquence. Authors utilize aesthetic elements such as colors, fonts, graphics, and layouts to shape the perception of information. Thoughtful…
We present an end-to-end trainable approach for Optical Character Recognition (OCR) on printed documents. Specifically, we propose a model that predicts a) a two-dimensional character grid (\emph{chargrid}) representation of a document…
Recent progress in multimodal large language models (MLLMs) has substantially improved document understanding, yet strong optical character recognition (OCR) performance on surface metrics does not guarantee faithful preservation of…
OCR errors are common in digitised historical archives significantly affecting their usability and value. Generative Language Models (LMs) have shown potential for correcting these errors using the context provided by the corrupted text and…
This manuscript introduces DharmaOCR Full and Lite, a pair of specialized small language models (SSLMs) for structured OCR that jointly optimize transcription quality, generation stability, and inference cost. It also presents…
Optical character recognition (OCR) technology has been widely used in various scenes, as shown in Figure 1. Designing a practical OCR system is still a meaningful but challenging task. In previous work, considering the efficiency and…