相关论文: Quantifying Character Similarity with Vision Trans…
Detection of semantic similarity plays a vital role in sentence matching. It requires to learn discriminative representations of natural language. Recently, owing to more and more sophisticated model architecture, impressive progress has…
Tokenisation - "the process of splitting text into atomic parts" (Brezina & Timperley, 2017: 1) - is a crucial step for corpus linguistics, as it provides the basis for any applicable quantitative method (e.g. collocations) while ensuring…
In this paper, we propose an end-to-end trainable framework for restoring historical documents content that follows the correct reading order. In this framework, two branches named character branch and layout branch are added behind the…
Scholars in the humanities rely heavily on ancient manuscripts to study history, religion, and socio-political structures in the past. Many efforts have been devoted to digitizing these precious manuscripts using OCR technology, but most…
Recent advancements in deep neural networks have markedly enhanced the performance of computer vision tasks, yet the specialized nature of these networks often necessitates extensive data and high computational power. Addressing these…
The digitization of historical folkloristic materials presents unique challenges due to diverse text layouts, varying print and handwriting styles, and linguistic variations. This study explores different optical character recognition (OCR)…
Handwritten Text Recognition (HTR) for Arabic-script languages benefits from cross-language joint training under low-resource conditions, particularly when using CRNN-based models that combine convolutional encoders with sequence modeling.…
We report upon the results of a research and prototype building project \emph{Worldly~OCR} dedicated to developing new, more accurate image-to-text conversion software for several languages and writing systems. These include the cursive…
The Transformer has quickly become the dominant architecture for various pattern recognition tasks due to its capacity for long-range representation. However, transformers are data-hungry models and need large datasets for training. In…
Pretrained multilingual language models are often assumed to be script-agnostic, yet their tokenizers can impose systematic costs on certain writing systems. We quantify this script tax by comparing two orthographic variants with identical…
In recent years, text-image joint pre-training techniques have shown promising results in various tasks. However, in Optical Character Recognition (OCR) tasks, aligning text instances with their corresponding text regions in images poses a…
We propose a framework for sequence-to-sequence contrastive learning (SeqCLR) of visual representations, which we apply to text recognition. To account for the sequence-to-sequence structure, each feature map is divided into different…
In this paper, we present token labeling -- a new training objective for training high-performance vision transformers (ViTs). Different from the standard training objective of ViTs that computes the classification loss on an additional…
The Hamming distance is ubiquitous in computing. Its computation gets expensive when one needs to compare a string against many strings. Quantum computers (QCs) may speed up the comparison. In this paper, we extend an existing algorithm for…
Modern language models are internally -- and mathematically -- distributions over $\it{token}$ strings rather than $\it{character}$ strings, posing numerous challenges for programmers building user applications on top of them. For example,…
The biggest challenge in the field of image processing is to recognize documents both in printed and handwritten format. Optical Character Recognition OCR is a type of document image analysis where scanned digital image that contains either…
A line of a bilingual document page may contain text words in regional language and numerals in English. For Optical Character Recognition (OCR) of such a document page, it is necessary to identify different script forms before running an…
Tasks that model the relation between pairs of tokens in a string are a vital part of understanding natural language. Such tasks, in general, require exhaustive pair-wise comparisons of tokens, thus having a quadratic runtime complexity in…
Vector quantization (VQ) is a key technique in high-resolution and high-fidelity image synthesis, which aims to learn a codebook to encode an image with a sequence of discrete codes and then generate an image in an auto-regression manner.…
When handling complicated text images (e.g., irregular structures, low resolution, heavy occlusion, and uneven illumination), existing supervised text recognition methods are data-hungry. Although these methods employ large-scale synthetic…