RUG-1-Pegasussers at SemEval-2022 Task 3: Data Generation Methods to Improve Recognizing Appropriate Taxonomic Word Relations
Wessel Poelman, Gijs Danoe, Esther Ploeger, Frank van den Berg, Tommaso Caselli, Lukas Edman
Abstract
This paper describes our system created for the SemEval 2022 Task 3: Presupposed Taxonomies - Evaluating Neural-network Semantics. This task is focused on correctly recognizing taxonomic word relations in English, French and Italian. We developed various datageneration techniques that expand the originally provided train set and show that all methods increase the performance of modelstrained on these expanded datasets. Our final system outperformed the baseline system from the task organizers by achieving an average macro F1 score of 79.6 on all languages, compared to the baseline’s 67.4.- Anthology ID:
- 2022.semeval-1.31
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- SemEval
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 247–254
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.31
- DOI:
- 10.18653/v1/2022.semeval-1.31
- Cite (ACL):
- Wessel Poelman, Gijs Danoe, Esther Ploeger, Frank van den Berg, Tommaso Caselli, and Lukas Edman. 2022. RUG-1-Pegasussers at SemEval-2022 Task 3: Data Generation Methods to Improve Recognizing Appropriate Taxonomic Word Relations. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 247–254, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- RUG-1-Pegasussers at SemEval-2022 Task 3: Data Generation Methods to Improve Recognizing Appropriate Taxonomic Word Relations (Poelman et al., SemEval 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.semeval-1.31.pdf