LIORI at SemEval-2021 Task 8: Ask Transformer for measurements
Adis Davletov, Denis Gordeev, Nikolay Arefyev, Emil Davletov
Abstract
This work describes our approach for subtasks of SemEval-2021 Task 8: MeasEval: Counts and Measurements which took the official first place in the competition. To solve all subtasks we use multi-task learning in a question-answering-like manner. We also use learnable scalar weights to weight subtasks’ contribution to the final loss in multi-task training. We fine-tune LUKE to extract quantity spans and we fine-tune RoBERTa to extract everything related to found quantities, including quantities themselves.- Anthology ID:
- 2021.semeval-1.178
- Volume:
- Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1249–1254
- Language:
- URL:
- https://aclanthology.org/2021.semeval-1.178
- DOI:
- 10.18653/v1/2021.semeval-1.178
- Cite (ACL):
- Adis Davletov, Denis Gordeev, Nikolay Arefyev, and Emil Davletov. 2021. LIORI at SemEval-2021 Task 8: Ask Transformer for measurements. In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021), pages 1249–1254, Online. Association for Computational Linguistics.
- Cite (Informal):
- LIORI at SemEval-2021 Task 8: Ask Transformer for measurements (Davletov et al., SemEval 2021)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2021.semeval-1.178.pdf