Related papers: StackMix and Blot Augmentations for Handwritten Te…
Large language models produce powerful text embeddings, but their causal attention mechanism restricts the flow of information from later to earlier tokens, degrading representation quality. While recent methods attempt to solve this by…
The adoption of tablets with touchscreens and styluses is increasing, and a key feature is converting handwriting to text, enabling search, indexing, and AI assistance. Meanwhile, vision-language models (VLMs) are now the go-to solution for…
Handwritten Text Line Segmentation (HTLS) is a low-level but important task for many higher-level document processing tasks like handwritten text recognition. It is often formulated in terms of semantic segmentation or object detection in…
Text data augmentation, i.e., the creation of new textual data from an existing text, is challenging. Indeed, augmentation transformations should take into account language complexity while being relevant to the target Natural Language…
Any finite set of training data is consistent with an infinite number of hypothetical algorithms that could have generated it. Studies have shown that when human children learn language, they consistently favor hypotheses based on…
In this report, we present our findings from benchmarking experiments for information extraction on historical handwritten marriage records Esposalles from IEHHR - ICDAR 2017 robust reading competition. The information extraction is modeled…
Representation learning on heterogeneous text-rich networks (HTRNs), which consist of multiple types of nodes and edges with each node associated with textual information, is essential for various real-world applications. Given the success…
In this paper, a robust multiscale neural network is proposed to recognize handwritten mathematical expressions and output LaTeX sequences, which can effectively and correctly focus on where each step of output should be concerned and has a…
The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological systems demonstrate highly sample-efficient…
The evaluation of Handwritten Text Recognition (HTR) systems has traditionally used metrics based on the edit distance between HTR and ground truth (GT) transcripts, at both the character and word levels. This is very adequate when the…
We present a CNN-BiLSTM system for the problem of offline English handwriting recognition, with extensive evaluations on the public IAM dataset, including the effects of model size, data augmentation and the lexicon. Our best model achieves…
Offline handwritten text recognition from images is an important problem for enterprises attempting to digitize large volumes of handmarked scanned documents/reports. Deep recurrent models such as Multi-dimensional LSTMs have been shown to…
Handwritten mathematical expression recognition (HMER) is an important research direction in handwriting recognition. The performance of HMER suffers from the two-dimensional structure of mathematical expressions (MEs). To address this…
The Mixup method has proven to be a powerful data augmentation technique in Computer Vision, with many successors that perform image mixing in a guided manner. One of the interesting research directions is transferring the underlying Mixup…
Large language models (LLMs) achieve optimal utility when their responses are grounded in external knowledge sources. However, real-world documents, such as annual reports, scientific papers, and clinical guidelines, frequently combine…
This paper summarizes our contributions to the document-grounded dialog tasks at the 9th and 10th Dialog System Technology Challenges (DSTC9 and DSTC10). In both iterations the task consists of three subtasks: first detect whether the…
Text classification algorithms investigate the intricate relationships between words or phrases and attempt to deduce the document's interpretation. In the last few years, these algorithms have progressed tremendously. Transformer…
Recently, the hybrid convolutional neural network hidden Markov model (CNN-HMM) has been introduced for offline handwritten Chinese text recognition (HCTR) and has achieved state-of-the-art performance. However, modeling each of the large…
The problem of detecting and recognizing text in natural scenes has proved to be more challenging than its counterpart in documents, with most of the previous work focusing on a single part of the problem. In this work, we propose new…
Since the rise of Large Language Models (LLMs) a couple of years ago, researchers in metaheuristics (MHs) have wondered how to use their power in a beneficial way within their algorithms. This paper introduces a novel approach that…