Automatic Detection of Word Sense Shift from Corpus Data

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F25%3A00142718" target="_blank" >RIV/00216224:14330/25:00142718 - isvavai.cz</a>

Result on the web

<a href="https://elex.link/elex2025/proceedings/" target="_blank" >https://elex.link/elex2025/proceedings/</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Automatic Detection of Word Sense Shift from Corpus Data

Original language description

Language evolves continuously, rendering static dictionaries quickly outdated. While previous research has addressed the automatic detection of new words, identifying subtler semantic changes in existing words remains a challenge. In this work, we propose a robust, language-independent methodology for the automatic detection of word sense shifts using diachronic corpus data. Our approach builds on the Adaptive Skip-Gram algorithm for word sense induction, enabling us to model polysemy directly from raw text without reliance on external sense inventories. We calculate the temporal distribution of induced senses and apply trend estimation techniques—specifically linear regression and the Theil–Sen estimator—to detect statistically significant shifts. This two-stage architecture decouples sense induction from trend analysis, increasing overall robustness and interpretability. Unlike traditional methods in lexical semantic change detection, which often target dramatic historical shifts, our method is designed to detect emerging or evolving senses over shorter timescales using large web corpora. We evaluate our method on Timestamped corpora in English and Czech and present several examples of detected sense shifts. The results demonstrate the feasibility of scalable, automatic sense shift detection and its potential applications in lexicography and linguistic research.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

9th Biennial Conference on Electronic Lexicography in the 21st Century, eLex 2025

ISBN

—

ISSN

2533-5626

e-ISSN

—

Number of pages

15

Pages from-to

237-251

Publisher name

Lexical Computing CZ s.r.o.

Place of publication

Bled, Slovenia

Event location

Bled, Slovenia

Event date

Nov 18, 2025

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—