SST-BERT at SemEval-2020 Task 1: Semantic Shift Tracing by Clustering in BERT-based Embedding Spaces

TL;DR

This paper presents an unsupervised method using BERT-based clustering of word occurrences to detect semantic shifts over time, outperforming baselines in multilingual settings.

Contribution

It introduces a novel clustering approach on contextualized embeddings to quantify semantic change without supervision.

Findings

Outperforms SemEval baselines across four languages

Effective clustering captures semantic shifts

Method is unsupervised and language-agnostic

Abstract

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.