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

Hadjer Khaldi, Farah Benamara, Camille Pradel, Nathalie Aussenac-Gilles


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 performance, 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.
Anthology ID:
2022.finnlp-1.23
Volume:
Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates (Hybrid)
Editors:
Chung-Chi Chen, Hen-Hsen Huang, Hiroya Takamura, Hsin-Hsi Chen
Venue:
FinNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
170–177
Language:
URL:
https://aclanthology.org/2022.finnlp-1.23
DOI:
10.18653/v1/2022.finnlp-1.23
Bibkey:
Cite (ACL):
Hadjer Khaldi, Farah Benamara, Camille Pradel, and Nathalie Aussenac-Gilles. 2022. How Can a Teacher Make Learning From Sparse Data Softer? Application to Business Relation Extraction. In Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP), pages 170–177, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
Cite (Informal):
How Can a Teacher Make Learning From Sparse Data Softer? Application to Business Relation Extraction (Khaldi et al., FinNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl-24-ws-corrections/2022.finnlp-1.23.pdf