IMS at SemEval-2020 Task 1: How low can you go? Dimensionality in Lexical Semantic Change Detection
This work addresses a specific issue in natural language processing for researchers, but it is incremental as it focuses on parameter tuning within an existing method.
The paper tackled the problem of optimizing dimensionality in lexical semantic change detection using Vector Initialization alignment, showing that it can outperform top-ranking models in Subtask 2 by reducing frequency-induced noise.
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.