Abstract
This paper describes our approach to emphasis selection for written text in visual media as a solution for SemEval 2020 Task 10. We used an ensemble of several different Transformer-based models and cast the task as a sequence labeling problem with two tags: ‘I’ as ‘emphasized’ and ‘O’ as ‘non-emphasized’ for each token in the text.- Anthology ID:
- 2020.semeval-1.220
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Venue:
- SemEval
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 1685–1690
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.220
- DOI:
- 10.18653/v1/2020.semeval-1.220
- Cite (ACL):
- Aleksandr Shatilov, Denis Gordeev, and Alexey Rey. 2020. Randomseed19 at SemEval-2020 Task 10: Emphasis Selection for Written Text in Visual Media. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1685–1690, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- Randomseed19 at SemEval-2020 Task 10: Emphasis Selection for Written Text in Visual Media (Shatilov et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/auto-file-uploads/2020.semeval-1.220.pdf