Communication Dans Un Congrès Année : 2025

Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain

Résumé

Generic pre-trained neural networks may struggle to produce good results in specialized domains like finance and insurance. This is due to a domain mismatch between training data and downstream tasks, as in-domain data are often scarce due to privacy constraints. In this work, we compare different pre-training strategies for LAYOUTLM. We show that using domain-relevant documents improves results on a named-entity recognition (NER) problem using a novel dataset of anonymized insurance-related financial documents called PAYSLIPS. Moreover, we show that we can achieve competitive results using a smaller and faster model.

Fichier principal
Vignette du fichier
2412.09341v1.pdf (3.24 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04877824 , version 1 (09-01-2025)

Licence

Identifiants

  • HAL Id : hal-04877824 , version 1

Citer

Benno Uthayasooriyar, Antoine Ly, Franck Vermet, Caio Corro. Training LayoutLM from Scratch for Efficient Named-Entity Recognition in the Insurance Domain. Joint Workshop of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on Large Language Models for Finance and Legal (LLMFinLegal), Jan 2025, Abu Dabi, United Arab Emirates. pp.1-9. ⟨hal-04877824⟩
253 Consultations
259 Téléchargements

Partager

  • More