Title | ||
---|---|---|
IMS at SemEval-2020 Task 1: How low can you go? Dimensionality in Lexical Semantic Change Detection |
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. |
Year | Venue | DocType |
---|---|---|
2020 | SemEval@COLING | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jens Kaiser | 1 | 0 | 0.68 |
Dominik Schlechtweg | 2 | 2 | 7.85 |
Sean Papay | 3 | 0 | 0.34 |
Sabine Schulte im Walde | 4 | 440 | 65.65 |