Abstract
This paper describes the emphasis selection system of the team TextLearner for SemEval 2020 Task 10: Emphasis Selection For Written Text in Visual Media. The system aims to learn the emphasis selection distribution using contextual representations extracted from pre-trained language models and a two-staged ranking model. The experimental results demonstrate the strong contextual representation power of the recent advanced transformer-based language model RoBERTa, which can be exploited using a simple but effective architecture on top.- Anthology ID:
- 2020.semeval-1.221
- Volume:
- Proceedings of the Fourteenth Workshop on Semantic Evaluation
- Month:
- December
- Year:
- 2020
- Address:
- Barcelona (online)
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- International Committee for Computational Linguistics
- Note:
- Pages:
- 1691–1697
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.221
- DOI:
- 10.18653/v1/2020.semeval-1.221
- Cite (ACL):
- Zhishen Yang, Lars Wolfsteller, and Naoaki Okazaki. 2020. TextLearner at SemEval-2020 Task 10: A Contextualized Ranking System in Solving Emphasis Selection in Text. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 1691–1697, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- TextLearner at SemEval-2020 Task 10: A Contextualized Ranking System in Solving Emphasis Selection in Text (Yang et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/starsem-semeval-split/2020.semeval-1.221.pdf
- Data
- MultiNLI