Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models
K Tatariya, V Araujo, T Bauwens… - arXiv preprint arXiv …, 2024 - arxiv.org
Pixel-based language models have emerged as a compelling alternative to subword-based
language modelling, particularly because they can represent virtually any script. PIXEL, a …
language modelling, particularly because they can represent virtually any script. PIXEL, a …
A Concise Survey of OCR for Low-Resource Languages
M Agarwal, A Anastasopoulos - … of the 4th Workshop on Natural …, 2024 - aclanthology.org
Modern natural language processing (NLP) techniques increasingly require substantial
amounts of data to train robust algorithms. Building such technologies for low-resource …
amounts of data to train robust algorithms. Building such technologies for low-resource …
[PDF][PDF] Digitalisation Workflows in the Age of Transformer Models: A Case Study in Digital Cultural Heritage
The advent of transformer architecture revolutionised the field of Artificial Intelligence (AI)
and its various applications. It is only recently that digitalisation of cultural heritage data has …
and its various applications. It is only recently that digitalisation of cultural heritage data has …