UWB @ DIACR-Ita: Lexical Semantic Change Detection with CCA and Orthogonal Transformation

TL;DR

This paper presents an unsupervised, language-independent method for detecting lexical semantic change over time using CCA and orthogonal transformations, successfully ranking first in the DIACR-Ita shared task.

Contribution

It introduces a novel approach combining CCA and orthogonal transformation to measure semantic shifts in lexical items across time periods.

Findings

Achieved first place in the DIACR-Ita shared task

Demonstrated effectiveness of CCA and orthogonal transformation in semantic change detection

Method is fully unsupervised and language independent

Abstract

In this paper, we describe our method for detection of lexical semantic change (i.e., word sense changes over time) for the DIACR-Ita shared task, where we ranked $1^{st}$. We examine semantic differences between specific words in two Italian corpora, chosen from different time periods. Our method is fully unsupervised and language independent. It consists of preparing a semantic vector space for each corpus, earlier and later. Then we compute a linear transformation between earlier and later spaces, using CCA and Orthogonal Transformation. Finally, we measure the cosines between the transformed vectors.