Abstract
To select tokens to be emphasised in short texts, a system mainly based on precomputed embedding models, such as BERT and ELMo, and LightGBM is proposed. Its performance is low. Additional analyzes suggest that its effectiveness is poor at predicting the highest emphasis scores while they are the most important for the challenge and that it is very sensitive to the specific instances provided during learning.
Cite
CITATION STYLE
Bestgen, Y. (2020). LAST at SemEval-2020 Task 10: Finding tokens to emphasise in short written texts with precomputed embedding models and LightGBM. In 14th International Workshops on Semantic Evaluation, SemEval 2020 - co-located 28th International Conference on Computational Linguistics, COLING 2020, Proceedings (pp. 1671–1677). International Committee for Computational Linguistics. https://doi.org/10.18653/v1/2020.semeval-1.218
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
