Extraction multi-étiquettes de relations en utilisant des couches de Transformer
This work addresses the problem of extracting complex relations from intelligence reports for French language processing, representing an incremental improvement over existing methods.
The paper tackles multi-label relation extraction in French texts by introducing the BTransformer18 model, which combines pre-trained BERT-family models with Transformer encoders, achieving a macro F1 score of 0.654 on the TextMine'25 dataset, particularly with CamemBERT-Large.
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.