Saved in:
Bibliographic Details
Main Authors: Le, Ngoc Luyen, Ngompé, Gildas Tagny
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.15619
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917932546654208
author Le, Ngoc Luyen
Ngompé, Gildas Tagny
author_facet Le, Ngoc Luyen
Ngompé, Gildas Tagny
contents In this article, we present the BTransformer18 model, a deep learning architecture designed for multi-label relation extraction in French texts. Our approach combines the contextual representation capabilities of pre-trained language models from the BERT family - such as BERT, RoBERTa, and their French counterparts CamemBERT and FlauBERT - with the power of Transformer encoders to capture long-term dependencies between tokens. Experiments conducted on the dataset from the TextMine'25 challenge show that our model achieves superior performance, particularly when using CamemBERT-Large, with a macro F1 score of 0.654, surpassing the results obtained with FlauBERT-Large. These results demonstrate the effectiveness of our approach for the automatic extraction of complex relations in intelligence reports.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15619
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Extraction multi-étiquettes de relations en utilisant des couches de Transformer
Le, Ngoc Luyen
Ngompé, Gildas Tagny
Computation and Language
Artificial Intelligence
In this article, we present the BTransformer18 model, a deep learning architecture designed for multi-label relation extraction in French texts. Our approach combines the contextual representation capabilities of pre-trained language models from the BERT family - such as BERT, RoBERTa, and their French counterparts CamemBERT and FlauBERT - with the power of Transformer encoders to capture long-term dependencies between tokens. Experiments conducted on the dataset from the TextMine'25 challenge show that our model achieves superior performance, particularly when using CamemBERT-Large, with a macro F1 score of 0.654, surpassing the results obtained with FlauBERT-Large. These results demonstrate the effectiveness of our approach for the automatic extraction of complex relations in intelligence reports.
title Extraction multi-étiquettes de relations en utilisant des couches de Transformer
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.15619