Effects of Pre- and Post-Processing on type-based Embeddings in Lexical Semantic Change Detection
This work provides incremental improvements for researchers in lexical semantic change detection by optimizing existing models with pre- and post-processing techniques.
The paper tackled the problem of optimizing lexical semantic change detection models by addressing the small data issue through pre-training on large corpora and refining on diachronic target corpora, and applying post-processing transformations, resulting in a guide for model application and optimization across various learning scenarios.
Lexical semantic change detection is a new and innovative research field. The optimal fine-tuning of models including pre- and post-processing is largely unclear. We optimize existing models by (i) pre-training on large corpora and refining on diachronic target corpora tackling the notorious small data problem, and (ii) applying post-processing transformations that have been shown to improve performance on synchronic tasks. Our results provide a guide for the application and optimization of lexical semantic change detection models across various learning scenarios.