SenseCluster at SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection
Amaru Cuba Gyllensten, Evangelia Gogoulou, Ariel Ekgren, Magnus Sahlgren
Abstract
We (Team Skurt) propose a simple method to detect lexical semantic change by clustering contextualized embeddings produced by XLM-R, using K-Means++. The basic idea is that contextualized embeddings that encode the same sense are located in close proximity in the embedding space. Our approach is both simple and generic, but yet performs relatively good in both sub-tasks of SemEval-2020 Task 1. We hypothesize that the main shortcoming of our method lies in the simplicity of the clustering method used.- Anthology ID:
- 2020.semeval-1.12
- 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:
- 112–118
- Language:
- URL:
- https://aclanthology.org/2020.semeval-1.12
- DOI:
- 10.18653/v1/2020.semeval-1.12
- Cite (ACL):
- Amaru Cuba Gyllensten, Evangelia Gogoulou, Ariel Ekgren, and Magnus Sahlgren. 2020. SenseCluster at SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 112–118, Barcelona (online). International Committee for Computational Linguistics.
- Cite (Informal):
- SenseCluster at SemEval-2020 Task 1: Unsupervised Lexical Semantic Change Detection (Cuba Gyllensten et al., SemEval 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2020.semeval-1.12.pdf