Related papers: Tokenization vs. Augmentation: A Systematic Study …
Handwriting recognition (HWR) using inertial measurement unit (IMU) data remains challenging due to variations in writing styles and the limited availability of datasets. Previous approaches often struggle with handwriting from unseen…
Purpose. Handwriting is one of the most frequently occurring patterns in everyday life and with it come challenging applications such as handwriting recognition (HWR), writer identification, and signature verification. In contrast to…
Data augmentation is usually used by supervised learning approaches for offline writer identification, but such approaches require extra training data and potentially lead to overfitting errors. In this study, a semi-supervised feature…
While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Model (LLM) development. Existing tokenizers often exhibit high…
Variation in language is ubiquitous and often systematically linked to regional, social, and contextual factors. Tokenizers split texts into smaller units and might behave differently for less common linguistic forms. This might affect…
Text independent writer identification is a challenging problem that differentiates between different handwriting styles to decide the author of the handwritten text. Earlier writer identification relied on handcrafted features to reveal…
Most online handwriting recognition systems require the use of specific writing surfaces to extract positional data. In this paper we present a online handwriting recognition system for word recognition which is based on inertial…
Offline handwriting recognition (HWR) has improved significantly with the advent of deep learning architectures in recent years. Nevertheless, it remains a challenging problem and practical applications often rely on post-processing…
Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…
In this paper, we demonstrate how a generative model can be used to build a better recognizer through the control of content and style. We are building an online handwriting recognizer from a modest amount of training samples. By training…
Online handwriting recognition using inertial measurement units opens up handwriting on paper as input for digital devices. Doing it on edge hardware improves privacy and lowers latency, but entails memory constraints. To address this, we…
Handwriting recognition has seen significant success with the use of deep learning. However, a persistent shortcoming of neural networks is that they are not well-equipped to deal with shifting data distributions. In the field of…
The choice of tokenizer can profoundly impact language model performance, yet accessible and reliable evaluations of tokenizer quality remain an open challenge. Inspired by scaling consistency, we show that smaller models can accurately…
Offline Handwritten Text Recognition (HTR) systems play a crucial role in applications such as historical document digitization, automatic form processing, and biometric authentication. However, their performance is often hindered by the…
Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the…
Handwriting recognition technology allows recognizing a written text from a given data. The recognition task can target letters, symbols, or words, and the input data can be a digital image or recorded by various sensors. A wide range of…
While transformer-based models achieve strong performance on text classification, we explore whether masking input tokens can further enhance their effectiveness. We propose token masking regularization, a simple yet theoretically motivated…
Subword tokenization has become the de-facto standard for tokenization, although comparative evaluations of subword vocabulary quality across languages are scarce. Existing evaluation studies focus on the effect of a tokenization algorithm…
Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…
The handwriting of an individual may vary substantially with factors such as mood, time, space, writing speed, writing medium and tool, writing topic, etc. It becomes challenging to perform automated writer verification/identification on a…