Passau21 at the NTCIR-16 FinNum-3 Task: Prediction Of Numerical Claims in the Earnings Calls with Transfer Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Passau21 at the NTCIR-16 FinNum-3 Task: Prediction Of Numerical Claims in the Earnings Calls with Transfer Learning

Résumé

The FinNum Task series aims at better understanding of numeral information in financial narratives. The goal of FinNum-3; on the English data part; is to have a fine-grained manager’s claim detection in the Earning Conference Calls (ECCs) with the help of Natural Language Processing (NLP). To succeed in the best performance for predicting in-claim and out-of-claim numerals, we propose the BERT (Bidirectional Encoder Representations from Transformers) base model , which is pre-trained on a large corpus of English data. The results of our model are 86.48% of macro-F1 score in the validation split and 87.12% of macro-F1 score in the test data.
Fichier non déposé

Dates et versions

hal-04022776 , version 1 (10-03-2023)

Identifiants

  • HAL Id : hal-04022776 , version 1

Citer

Alaa Alhamzeh, Kürsad Lacin, Elod Egyed-Zsigmond. Passau21 at the NTCIR-16 FinNum-3 Task: Prediction Of Numerical Claims in the Earnings Calls with Transfer Learning. Proceedings of the 16th NTCIR Conference on Evaluation of Information Access Technologies, Jun 2022, Tokyo, Japan. ⟨hal-04022776⟩
19 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More