IMS at SemEval-2020 Task 1: How Low Can You Go? Dimensionality in Lexical Semantic Change Detection

Jens Kaiser, Dominik Schlechtweg, Sean Papay, Sabine Schulte im Walde


Abstract
We present the results of our system for SemEval-2020 Task 1 that exploits a commonly used lexical semantic change detection model based on Skip-Gram with Negative Sampling. Our system focuses on Vector Initialization (VI) alignment, compares VI to the currently top-ranking models for Subtask 2 and demonstrates that these can be outperformed if we optimize VI dimensionality. We demonstrate that differences in performance can largely be attributed to model-specific sources of noise, and we reveal a strong relationship between dimensionality and frequency-induced noise in VI alignment. Our results suggest that lexical semantic change models integrating vector space alignment should pay more attention to the role of the dimensionality parameter.
Anthology ID:
2020.semeval-1.8
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:
81–89
Language:
URL:
https://aclanthology.org/2020.semeval-1.8
DOI:
10.18653/v1/2020.semeval-1.8
Bibkey:
Cite (ACL):
Jens Kaiser, Dominik Schlechtweg, Sean Papay, and Sabine Schulte im Walde. 2020. IMS at SemEval-2020 Task 1: How Low Can You Go? Dimensionality in Lexical Semantic Change Detection. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 81–89, Barcelona (online). International Committee for Computational Linguistics.
Cite (Informal):
IMS at SemEval-2020 Task 1: How Low Can You Go? Dimensionality in Lexical Semantic Change Detection (Kaiser et al., SemEval 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.semeval-1.8.pdf