Abstract
We describe our system (TüKaPo) submitted for Task 6: DeftEval, at SemEval 2020. We developed a hybrid approach that combined existing CNN and RNN methods and investigated the impact of purely-syntactic and semantic features on the task of definition extraction. Our final model achieved a F1-score of 0.6851 in subtask 1, i.e, sentence classification.- Anthology ID:
- 2020.semeval-1.95
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Editors:
- Aurelie Herbelot, Xiaodan Zhu, Alexis Palmer, Nathan Schneider, Jonathan May, Ekaterina Shutova
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 724–729
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.95
- DOI:
- 10.18653/v1/2020.semeval-1.95
- Cite (ACL):
- Madeeswaran Kannan and Haemanth Santhi Ponnusamy. 2020. TüKaPo at SemEval-2020 Task 6: Def(n)tly Not BERT: Definition Extraction Using pre-BERT Methods in a post-BERT World. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 724–729, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- TüKaPo at SemEval-2020 Task 6: Def(n)tly Not BERT: Definition Extraction Using pre-BERT Methods in a post-BERT World (Kannan & Santhi Ponnusamy, SemEval 2020)
- PDF:
- https://preview.aclanthology.org/fix-volume-bibkeys/2020.semeval-1.95.pdf
- Data
- DEFT Corpus