Abstract
This paper describes the model we apply in the SemEval-2020 Task 10. We formalize the task of emphasis selection as a simplified query-based machine reading comprehension (MRC) task, i.e. answering a fixed question of “Find candidates for emphasis”. We propose our subword puzzle encoding mechanism and subword fusion layer to align and fuse subwords. By introducing the semantic prior knowledge of the informative query and some other techniques, we attain the 7th place during the evaluation phase and the first place during train phase.
Cite
CITATION STYLE
Guo, C., Hou, X., Ren, J., Jiang, L., Mo, Y., Yang, H., & Shen, J. (2020). FPAI at SemEval-2020 Task 10: A Query Enhanced Model with RoBERTa for Emphasis Selection. In 14th International Workshops on Semantic Evaluation, SemEval 2020 - co-located 28th International Conference on Computational Linguistics, COLING 2020, Proceedings (pp. 1652–1657). International Committee for Computational Linguistics. https://doi.org/10.18653/v1/2020.semeval-1.215
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
