TermEval 2020 : shared task on automatic term extraction using the Annotated Corpora for term Extraction Research (ACTER) dataset
- Author
- Ayla Rigouts Terryn, Veronique Hoste (UGent) , Patrick Drouin and Els Lefever (UGent)
- Organization
- Abstract
- The TermEval 2020 shared task provided a platform for researchers to work on automatic term extraction (ATE) with the same dataset: the Annotated Corpora for Term Extraction Research (ACTER). The dataset covers three languages (English, French, and Dutch) and four domains, of which the domain of heart failure was kept as a held-out test set on which final f1-scores were calculated. The aim was to provide a large, transparent, qualitatively annotated, and diverse dataset to the ATE research community, with the goal of promoting comparative research and thus identifying strengths and weaknesses of various state-of-the-art methodologies. The results show a lot of variation between different systems and illustrate how some methodologies reach higher precision or recall, how different systems extract different types of terms, how some are exceptionally good at finding rare terms, or are less impacted by term length. The current contribution offers an overview of the shared task with a comparative evaluation, which complements the individual papers by all participants.
- Keywords
- LT3, ATE, automatic term extraction, terminology
Downloads
-
Rigouts Terryn EtAl 2020 TermEval overview paper.pdf
- full text (Published version)
- |
- open access
- |
- |
- 349.31 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8661811
- MLA
- Rigouts Terryn, Ayla, et al. “TermEval 2020 : Shared Task on Automatic Term Extraction Using the Annotated Corpora for Term Extraction Research (ACTER) Dataset.” 6th International Workshop on Computational Terminology (COMPUTERM 2020), Proceedings, edited by Béatrice Daile et al., European Language Resources Association (ELRA), 2020, pp. 85–94.
- APA
- Rigouts Terryn, A., Hoste, V., Drouin, P., & Lefever, E. (2020). TermEval 2020 : shared task on automatic term extraction using the Annotated Corpora for term Extraction Research (ACTER) dataset. In B. Daile, K. Kageura, & A. Rigouts Terryn (Eds.), 6th International Workshop on Computational Terminology (COMPUTERM 2020), Proceedings (pp. 85–94). European Language Resources Association (ELRA).
- Chicago author-date
- Rigouts Terryn, Ayla, Veronique Hoste, Patrick Drouin, and Els Lefever. 2020. “TermEval 2020 : Shared Task on Automatic Term Extraction Using the Annotated Corpora for Term Extraction Research (ACTER) Dataset.” In 6th International Workshop on Computational Terminology (COMPUTERM 2020), Proceedings, edited by Béatrice Daile, Kyo Kageura, and Ayla Rigouts Terryn, 85–94. European Language Resources Association (ELRA).
- Chicago author-date (all authors)
- Rigouts Terryn, Ayla, Veronique Hoste, Patrick Drouin, and Els Lefever. 2020. “TermEval 2020 : Shared Task on Automatic Term Extraction Using the Annotated Corpora for Term Extraction Research (ACTER) Dataset.” In 6th International Workshop on Computational Terminology (COMPUTERM 2020), Proceedings, ed by. Béatrice Daile, Kyo Kageura, and Ayla Rigouts Terryn, 85–94. European Language Resources Association (ELRA).
- Vancouver
- 1.Rigouts Terryn A, Hoste V, Drouin P, Lefever E. TermEval 2020 : shared task on automatic term extraction using the Annotated Corpora for term Extraction Research (ACTER) dataset. In: Daile B, Kageura K, Rigouts Terryn A, editors. 6th International Workshop on Computational Terminology (COMPUTERM 2020), Proceedings. European Language Resources Association (ELRA); 2020. p. 85–94.
- IEEE
- [1]A. Rigouts Terryn, V. Hoste, P. Drouin, and E. Lefever, “TermEval 2020 : shared task on automatic term extraction using the Annotated Corpora for term Extraction Research (ACTER) dataset,” in 6th International Workshop on Computational Terminology (COMPUTERM 2020), Proceedings, Marsaille, france, 2020, pp. 85–94.
@inproceedings{8661811,
abstract = {{The TermEval 2020 shared task provided a platform for researchers to work on automatic term extraction (ATE) with the same dataset: the Annotated Corpora for Term Extraction Research (ACTER). The dataset covers three languages (English, French, and Dutch) and four domains, of which the domain of heart failure was kept as a held-out test set on which final f1-scores were calculated. The aim was to provide a large, transparent, qualitatively annotated, and diverse dataset to the ATE research community, with the goal of promoting comparative research and thus identifying strengths and weaknesses of various state-of-the-art methodologies. The results show a lot of variation between different systems and illustrate how some methodologies reach higher precision or recall, how different systems extract different types of terms, how some are exceptionally good at finding rare terms, or are less impacted by term length. The current contribution offers an overview of the shared task with a comparative evaluation, which complements the individual papers by all participants.}},
author = {{Rigouts Terryn, Ayla and Hoste, Veronique and Drouin, Patrick and Lefever, Els}},
booktitle = {{6th International Workshop on Computational Terminology (COMPUTERM 2020), Proceedings}},
editor = {{Daile, Béatrice and Kageura, Kyo and Rigouts Terryn, Ayla}},
isbn = {{9791095546573}},
keywords = {{LT3,ATE,automatic term extraction,terminology}},
language = {{eng}},
location = {{Marsaille, france}},
pages = {{85--94}},
publisher = {{European Language Resources Association (ELRA)}},
title = {{TermEval 2020 : shared task on automatic term extraction using the Annotated Corpora for term Extraction Research (ACTER) dataset}},
url = {{https://www.aclweb.org/anthology/2020.computerm-1.12/}},
year = {{2020}},
}