How Can a Teacher Make Learning From Sparse Data Softer? Application to Business Relation Extraction - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

How Can a Teacher Make Learning From Sparse Data Softer? Application to Business Relation Extraction

Résumé

Business Relation Extraction between market entities is a challenging information extraction task that suffers from data imbalance due to the over-representation of negative relations (also known as No-relation or Others) compared to positive relations that corresponds to the taxonomy of relations of interest. This paper proposes a novel solution to tackle this problem, relying on binary soft-labels supervision generated by an approach based on knowledge distillation. When evaluated on a business relation extraction dataset, the results suggest that the proposed approach improves the overall performances, beating state-of-the art solutions for data imbalance. In particular, it improves the extraction of under-represented relations as well as the detection of false negatives.
Fichier principal
Vignette du fichier
4.pdf (394.88 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03730414 , version 1 (24-08-2022)

Identifiants

  • HAL Id : hal-03730414 , version 1

Citer

Farah Benamara, Hadjer Khaldi, Camille Pradel, Nathalie Aussenac-Gilles. How Can a Teacher Make Learning From Sparse Data Softer? Application to Business Relation Extraction. 4th Workshop on Financial Technology and Natural Language Processing (FinNLP @ IJCAI 2022), Jul 2022, Vienna, Austria. pp.22-28. ⟨hal-03730414⟩
119 Consultations
59 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More