no code implementations • 26 May 2022 • Nguyen Hong Son, Hieu M. Vu, Tuan-Anh D. Nguyen, Minh-Tien Nguyen
This paper introduces a new information extraction model for business documents.
1 code implementation • NAACL 2022 • Shumpei Inoue, Tsungwei Liu, Nguyen Hong Son, Minh-Tien Nguyen
To support the picker, we design two label creation methods (soft and hard labels), which can work in cases of no annotation data for the omitted tokens.
no code implementations • 2 Jun 2021 • Tuan-Anh D. Nguyen, Hieu M. Vu, Nguyen Hong Son, Minh-Tien Nguyen
Firstly, we introduce a new query-based IE model that employs span extraction instead of using the common sequence labeling approach.
no code implementations • 6 Mar 2020 • Minh-Tien Nguyen, Viet-Anh Phan, Le Thai Linh, Nguyen Hong Son, Le Tien Dung, Miku Hirano, Hajime Hotta
This paper presents a practical approach to fine-grained information extraction.