Skip to Main content Skip to Navigation
Conference papers

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

Abstract : 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.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03730414
Contributor : Farah Benamara Connect in order to contact the contributor
Submitted on : Wednesday, August 24, 2022 - 3:37:44 PM
Last modification on : Monday, August 29, 2022 - 11:07:31 AM

File

4.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03730414, version 1

Citation

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⟩

Share

Metrics

Record views

40

Files downloads

2