Abstract
This paper describes the approaches used by the Discovery Team to solve SemEval-2020 Task 1 - Unsupervised Lexical Semantic Change Detection. The proposed method is based on clustering of BERT contextual embeddings, followed by a comparison of cluster distributions across time. The best results were obtained by an ensemble of this method and static Word2Vec embeddings. According to the official results, our approach proved the best for Latin in Subtask 2.
Cite
CITATION STYLE
Martinc, M., Montariol, S., Pivovarova, L., & Zosa, E. (2020). Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings not Always Better Than Static for Semantic Change Detection. In 14th International Workshops on Semantic Evaluation, SemEval 2020 - co-located 28th International Conference on Computational Linguistics, COLING 2020, Proceedings (pp. 67–73). International Committee for Computational Linguistics. https://doi.org/10.18653/v1/2020.semeval-1.6
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
