CL-IMS @ DIACR-Ita: Volente o Nolente: BERT does not outperform SGNS on Semantic Change Detection
This work addresses lexical semantic change detection for Italian linguists, but it is incremental as it shows limited improvement over existing methods.
The paper tackled semantic change detection for Italian using BERT embeddings, achieving an accuracy of 0.72 and ranking 5th out of 8 in the DIACR-Ita shared task, but found that BERT did not outperform simpler SGNS methods despite tuning on English data.
We present the results of our participation in the DIACR-Ita shared task on lexical semantic change detection for Italian. We exploit Average Pairwise Distance of token-based BERT embeddings between time points and rank 5 (of 8) in the official ranking with an accuracy of $.72$. While we tune parameters on the English data set of SemEval-2020 Task 1 and reach high performance, this does not translate to the Italian DIACR-Ita data set. Our results show that we do not manage to find robust ways to exploit BERT embeddings in lexical semantic change detection.