Publications Workshop · 2025

DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization

P. P. M. Chau, S. Bakkali, A. Doucet

IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), VisionDocs, pp. 1213–1222

In one paragraph

A domain-adaptive abstractive summarisation framework for administrative documents: pre-training on OCR-transcribed text and fine-tuning with question-answer pairs, to cope with domain terminology, OCR errors and scarce annotations.

Cite

@inproceedings{chau2025docsum,
  title     = {{DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization}},
  author    = {Chau, Phan Phuong Mai and Bakkali, Souhail and Doucet, Antoine},
  booktitle = {2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)},
  pages     = {1213--1222},
  year      = {2025},
  doi       = {10.1109/WACVW65960.2025.00144},
  url       = {https://arxiv.org/abs/2412.08196}
}