DiaSense at SemEval-2020 Task 1: Modeling Sense Change via Pre-trained BERT Embeddings

Christin Beck


Abstract
This paper describes DiaSense, a system developed for Task 1 ‘Unsupervised Lexical Semantic Change Detection’ of SemEval 2020. In DiaSense, contextualized word embeddings are used to model word sense changes. This allows for the calculation of metrics which mimic human intuitions about the semantic relatedness between individual use pairs of a target word for the assessment of lexical semantic change. DiaSense is able to detect lexical semantic change in English, German, Latin and Swedish (accuracy = 0.728). Moreover, DiaSense differentiates between weak and strong change.
Anthology ID:
2020.semeval-1.4
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:
50–58
Language:
URL:
https://aclanthology.org/2020.semeval-1.4
DOI:
10.18653/v1/2020.semeval-1.4
Bibkey:
Cite (ACL):
Christin Beck. 2020. DiaSense at SemEval-2020 Task 1: Modeling Sense Change via Pre-trained BERT Embeddings. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 50–58, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
DiaSense at SemEval-2020 Task 1: Modeling Sense Change via Pre-trained BERT Embeddings (Beck, SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.4.pdf