Communication Dans Un Congrès Année : 2024

Mention-Agnostic Information Extraction for Ontological Annotation of Biomedical Articles

Résumé

Biomedical information extraction is crucial for advancing research, enhancing healthcare, and discovering treatments by efficiently analyzing extensive data. Given the extensive amount of biomedical data available, automated information extraction methods are necessary due to manual extraction's labor-intensive, expertisedependent, and costly nature. In this paper, we propose a novel two-stage system for information extraction where we annotate biomedical articles based on a specific ontology (HOIP). The major challenge is annotating relation between biomedical processes often not explicitly mentioned in text articles. Here, we first predict the candidate processes and then determine the relationships between these processes without relying on mentions. The experimental results show promising outcomes in mentionagnostic process identification using Large Language Models (LLMs). In relation classification, our proposed BERT-based models outperform LLMs significantly. The end-to-end evaluation results suggest the difficulty of this task and room for improvement in both process identification and relation classification.

Fichier principal
Vignette du fichier
2024.bionlp-1.37.pdf (455.83 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04916867 , version 1 (28-01-2025)

Licence

Identifiants

Citer

Oumaima El Khettari, Noriki Nishida, Shanshan Liu, Rumana Ferdous Munne, Yuki Yamagata, et al.. Mention-Agnostic Information Extraction for Ontological Annotation of Biomedical Articles. Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, Aug 2024, Bangkok, Thailand. pp.457-473, ⟨10.18653/v1/2024.bionlp-1.37⟩. ⟨hal-04916867⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More