Advanced search
2 files | 252.05 KB Add to list

Extracting fine-grained economic events from business news

Gilles Jacobs (UGent) and Veronique Hoste (UGent)
Author
Organization
Project
Abstract
Based on a recently developed fine-grained event extraction dataset for the economic domain, we present in a pilot study for supervised economic event extraction. We investigate how a state-of-the-art model for event extraction performs on the trigger and argument identification and classification. While F1-scores of above 50{%} are obtained on the task of trigger identification, we observe a large gap in performance compared to results on the benchmark ACE05 dataset. We show that single-token triggers do not provide sufficient discriminative information for a fine-grained event detection setup in a closed domain such as economics, since many classes have a large degree of lexico-semantic and contextual overlap.
Keywords
event extraction, economic events, fine-grained financial information extraction, business news, lt3

Downloads

  • 2020.fnp-1.36.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 208.38 KB
  • (...).pdf
    • peer review report
    • |
    • UGent only
    • |
    • PDF
    • |
    • 43.67 KB

Citation

Please use this url to cite or link to this publication:

MLA
Jacobs, Gilles, and Veronique Hoste. “Extracting Fine-Grained Economic Events from Business News.” Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, edited by Mahmoud El-Haj et al., COLING, 2020, pp. 235–45.
APA
Jacobs, G., & Hoste, V. (2020). Extracting fine-grained economic events from business news. In M. El-Haj, V. Athanasakou, S. Ferradans, C. Salzedo, A. Elhag, H. Bouamor, … N. Pittaras (Eds.), Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation (pp. 235–245). Online (Barcelona, Spain): COLING.
Chicago author-date
Jacobs, Gilles, and Veronique Hoste. 2020. “Extracting Fine-Grained Economic Events from Business News.” In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, edited by Mahmoud El-Haj, Vasiliki Athanasakou, Sira Ferradans, Catherine Salzedo, Ans Elhag, Houda Bouamor, Marina Litvak, Paul Rayson, George Giannakopoulos, and Nikiforos Pittaras, 235–45. COLING.
Chicago author-date (all authors)
Jacobs, Gilles, and Veronique Hoste. 2020. “Extracting Fine-Grained Economic Events from Business News.” In Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, ed by. Mahmoud El-Haj, Vasiliki Athanasakou, Sira Ferradans, Catherine Salzedo, Ans Elhag, Houda Bouamor, Marina Litvak, Paul Rayson, George Giannakopoulos, and Nikiforos Pittaras, 235–245. COLING.
Vancouver
1.
Jacobs G, Hoste V. Extracting fine-grained economic events from business news. In: El-Haj M, Athanasakou V, Ferradans S, Salzedo C, Elhag A, Bouamor H, et al., editors. Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation. COLING; 2020. p. 235–45.
IEEE
[1]
G. Jacobs and V. Hoste, “Extracting fine-grained economic events from business news,” in Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, Online (Barcelona, Spain), 2020, pp. 235–245.
@inproceedings{8711943,
  abstract     = {{Based on a recently developed fine-grained event extraction dataset for the economic domain, we present in a pilot study for supervised economic event extraction. We investigate how a state-of-the-art model for event extraction performs on the trigger and argument identification and classification. While F1-scores of above 50{%} are obtained on the task of trigger identification, we observe a large gap in performance compared to results on the benchmark ACE05 dataset. We show that single-token triggers do not provide sufficient discriminative information for a fine-grained event detection setup in a closed domain such as economics, since many classes have a large degree of lexico-semantic and contextual overlap.}},
  author       = {{Jacobs, Gilles and Hoste, Veronique}},
  booktitle    = {{Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation}},
  editor       = {{El-Haj, Mahmoud and Athanasakou, Vasiliki and Ferradans, Sira and Salzedo, Catherine and Elhag, Ans and Bouamor, Houda and Litvak, Marina and Rayson, Paul and Giannakopoulos, George and Pittaras, Nikiforos}},
  keywords     = {{event extraction,economic events,fine-grained financial information extraction,business news,lt3}},
  language     = {{eng}},
  location     = {{Online (Barcelona, Spain)}},
  pages        = {{235--245}},
  publisher    = {{COLING}},
  title        = {{Extracting fine-grained economic events from business news}},
  url          = {{https://www.aclweb.org/anthology/2020.fnp-1.36}},
  year         = {{2020}},
}