7 papers
Hybrid Retrieval-Augmented Generation for Robust Multilingual Document Question Answering
Anthony Mudet, Souhail Bakkali
Large-scale digitization initiatives have unlocked massive collections of historical newspapers, yet effective computational access remains hindered by OCR corruption, multilingual…
Evaluating the Impact of Khmer Font Types on Text Recognition
Vannkinh Nom, Souhail Bakkali, Muhammad Muzzamil Luqman +2
Text recognition is significantly influenced by font types, especially for complex scripts like Khmer. The variety of Khmer fonts, each with its unique character structure, present…
DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization
Phan Phuong Mai Chau, Souhail Bakkali, Antoine Doucet
Abstractive summarization has made significant strides in condensing and rephrasing large volumes of text into coherent summaries. However, summarizing administrative documents pre…
GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification
Souhail Bakkali, Sanket Biswas, Zuheng Ming +4
Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pr…
KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark
Vannkinh Nom, Souhail Bakkali, Muhammad Muzzamil Luqman +2
Developing effective scene text detection and recognition models hinges on extensive training data, which can be both laborious and costly to obtain, especially for low-resourced l…
Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting
Omar Hamed, Souhail Bakkali, Marie-Francine Moens +2
This work addresses the need for a balanced approach between performance and efficiency in scalable production environments for visually-rich document understanding (VDU) tasks. Cu…