Abstract
We propose an end-to-end model that takes as input the text and corresponding to each word gives the probability of the word to be emphasized. Our results show that transformer-based models are particularly effective in this task. We achieved an evaluation score of 0.810 and were ranked third on the leaderboard.- Anthology ID:
- 2020.semeval-1.217
- 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:
- 1665–1670
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.217
- DOI:
- 10.18653/v1/2020.semeval-1.217
- Cite (ACL):
- Vipul Singhal, Sahil Dhull, Rishabh Agarwal, and Ashutosh Modi. 2020. IITK at SemEval-2020 Task 10: Transformers for Emphasis Selection. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1665–1670, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- IITK at SemEval-2020 Task 10: Transformers for Emphasis Selection (Singhal et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2020.semeval-1.217.pdf
- Code
- SahilDhull/emphasis_selection