Detecting forged receipts with domain-specific ontology-based entities & relations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Detecting forged receipts with domain-specific ontology-based entities & relations

Résumé

In this paper, we tackle the task of document fraud detection. We consider that this task can be addressed with natural language processing techniques. We treat it as a regression-based approach, by taking advantage of a pre-trained language model in order to represent the textual content, and by enriching the representation with domainspecific ontology-based entities and relations. We emulate an entity-based approach by comparing different types of input: raw text, extracted entities and a triple-based reformulation of the document content. For our experimental setup, we utilize the single freely available dataset of forged receipts, and we provide a deep analysis of our results in regard to the efficiency of our methods. Our findings show interesting correlations between the types of ontology relations (e.g., has address, amounts to), types of entities (product, company, etc.) and the performance of a regression-based language model that could help to study the transfer learning from natural language processing (NLP) methods to boost the performance of existing fraud detection systems.
Fichier principal
Vignette du fichier
ICDAR_2023_Detecting_Forged_Receipts_with_Domain_specific_Ontology_based_Entities_Relations (1).pdf (9.48 Mo) Télécharger le fichier
ICDAR_2023_Detecting_Forged_Receipts_with_Domain_specific_Ontology_based_Entities_Relations.pdf (9.48 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04296021 , version 1 (20-11-2023)

Identifiants

Citer

Beatriz Martínez Tornés, Emanuela Boros, Petra Gomez-Krämer, Antoine Doucet, Jean-Marc Ogier. Detecting forged receipts with domain-specific ontology-based entities & relations. ICDAR, Aug 2023, San José, United States. pp.184-199, ⟨10.1007/978-3-031-41682-8_12⟩. ⟨hal-04296021⟩

Collections

UNIV-ROCHELLE
3 Consultations
20 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More