The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing

TL;DR

This paper presents a novel model editing approach that enhances recognition of low-resource alphabets, enabling faster generalization and transfer learning to diverse and underrepresented scripts, including historical and non-Latin texts.

Contribution

It introduces a new method leveraging model editing for low-resource alphabet recognition, outperforming meta-learning in domain merging and enabling rapid adaptation to new scripts.

Findings

Significant performance improvements in transfer learning to new alphabets.

Effective out-of-domain evaluation on historical ciphered texts.

Model editing enhances generalization to low-resource and unseen scripts.

Abstract

Achieving robustness in recognition systems across diverse domains is crucial for their practical utility. While ample data availability is usually assumed, low-resource languages, such as ancient manuscripts and non-western languages, tend to be kept out of the equations of massive pretraining and foundational techniques due to an under representation. In this work, we aim for building models which can generalize to new distributions of data, such as alphabets, faster than centralized fine-tune strategies. For doing so, we take advantage of the recent advancements in model editing to enhance the incorporation of unseen scripts (low-resource learning). In contrast to state-of-the-art meta-learning, we showcase the effectiveness of domain merging in sparse distributions of data, with agnosticity of its relation to the overall distribution or any other prototyping necessity. Even when using the same exact training data, our experiments showcase significant performance boosts in \textbf{transfer learning} to new alphabets and \textbf{out-of-domain evaluation} in challenging domain shifts, including historical ciphered texts and non-Latin scripts. This research contributes a novel approach into building models that can easily adopt under-represented alphabets and, therefore, enable document recognition to a wider set of contexts and cultures.