SST-BERT at SemEval-2020 Task 1: Semantic Shift Tracing by Clustering in BERT-based Embedding Spaces
This work addresses the challenge of detecting semantic shifts over time for linguists and NLP researchers, but it is incremental as it builds on existing BERT-based methods.
The paper tackled the problem of unsupervised lexical semantic change detection by clustering BERT-based embeddings of word occurrences to identify meaning shifts, achieving results that surpassed all provided SemEval baselines across four languages.
Lexical semantic change detection (also known as semantic shift tracing) is a task of identifying words that have changed their meaning over time. Unsupervised semantic shift tracing, focal point of SemEval2020, is particularly challenging. Given the unsupervised setup, in this work, we propose to identify clusters among different occurrences of each target word, considering these as representatives of different word meanings. As such, disagreements in obtained clusters naturally allow to quantify the level of semantic shift per each target word in four target languages. To leverage this idea, clustering is performed on contextualized (BERT-based) embeddings of word occurrences. The obtained results show that our approach performs well both measured separately (per language) and overall, where we surpass all provided SemEval baselines.