A Majority Voting Strategy of a SciBERT-based Ensemble Models for Detecting Entities in the Astrophysics Literature (Shared Task) - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A Majority Voting Strategy of a SciBERT-based Ensemble Models for Detecting Entities in the Astrophysics Literature (Shared Task)

Résumé

Detecting Entities in the Astrophysics Literature (DEAL) is a proposed shared task in the scope of the first Workshop on Information Extraction from Scientific Publications (WIESP) at AACL-IJCNLP 2022. It aims to propose systems identifying astrophysical named entities. This article presents our system based on a majority voting strategy of an ensemble composed of 32 SciBERT models. The system we propose is ranked second and outperforms the baseline provided by the organisers by achieving an F1 score of 0.7993 and a Matthews Correlation Coefficient (MCC) score of 0.8978 in the testing phase.
Fichier principal
Vignette du fichier
2022.wiesp-1.17.pdf (323.52 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04425922 , version 1 (30-01-2024)

Identifiants

  • HAL Id : hal-04425922 , version 1

Citer

Atilla Kaan Alkan, Cyril Grouin, Fabian Schüssler, Pierre Zweigenbaum. A Majority Voting Strategy of a SciBERT-based Ensemble Models for Detecting Entities in the Astrophysics Literature (Shared Task). First Workshop on Information Extraction from Scientific Publications, Association for Computational Linguistics, Nov 2022, Online, Taiwan. pp.131-139. ⟨hal-04425922⟩
6 Consultations
13 Téléchargements

Partager

Gmail Facebook X LinkedIn More