A Semantic Distance Metric Learning approach for Lexical Semantic Change Detection

TL;DR

This paper introduces a supervised two-stage method for detecting lexical semantic change over time, leveraging sense-aware encoders and a learned distance metric, demonstrating strong multilingual performance and improvements over existing methods.

Contribution

The paper presents a novel supervised approach using sense-aware encoders and a learned distance metric for lexical semantic change detection, outperforming previous methods on benchmark datasets.

Findings

Strong performance on multiple language datasets

Significant improvements on WiC benchmarks

Effective sense-aware semantic comparison

Abstract

Detecting temporal semantic changes of words is an important task for various NLP applications that must make time-sensitive predictions. Lexical Semantic Change Detection (SCD) task involves predicting whether a given target word, $w$, changes its meaning between two different text corpora, $C_1$ and $C_2$. For this purpose, we propose a supervised two-staged SCD method that uses existing Word-in-Context (WiC) datasets. In the first stage, for a target word $w$, we learn two sense-aware encoders that represent the meaning of $w$ in a given sentence selected from a corpus. Next, in the second stage, we learn a sense-aware distance metric that compares the semantic representations of a target word across all of its occurrences in $C_1$ and $C_2$. Experimental results on multiple benchmark datasets for SCD show that our proposed method achieves strong performance in multiple languages. Additionally, our method achieves significant improvements on WiC benchmarks compared to a sense-aware encoder with conventional distance functions. Source code is available at https://github.com/LivNLP/svp-sdml .