1 code implementation • 28 Apr 2023 • Seif Laatiri, Pirashanth Ratnamogan, Joel Tang, Laurent Lam, William Vanhuffel, Fabien Caspani
Advances in the Visually-rich Document Understanding (VrDU) field and particularly the Key-Information Extraction (KIE) task are marked with the emergence of efficient Transformer-based approaches such as the LayoutLM models.
no code implementations • 21 Apr 2023 • Laurent Lam, Pirashanth Ratnamogan, Joël Tang, William Vanhuffel, Fabien Caspani
Our research showed that when dealing with clean and relatively short entities, it is still best to use token classification-based approach, while the QA approach could be a good alternative for noisy environment or long entities use-cases.
no code implementations • 26 Oct 2022 • Mathieu Grosso, Pirashanth Ratnamogan, Alexis Mathey, William Vanhuffel, Michael Fotso Fotso
In this context, we decided to focus on a new task: Domain Adaptation of a pre-trained mNMT model on a single pair of language while trying to maintain model quality on generic domain data for all language pairs.
no code implementations • 7 Nov 2021 • Ismail Oussaid, William Vanhuffel, Pirashanth Ratnamogan, Mhamed Hajaiej, Alexis Mathey, Thomas Gilles
Information extraction (IE) from documents is an intensive area of research with a large set of industrial applications.