ConShift: Sense-based Language Variation Analysis using Flexible Alignment
Clare Arrington, Mauricio Gruppi, Sibel Adali
Abstract
We introduce ConShift, a family of alignment-based algorithms that enable semantic variation analysis at the sense-level. Using independent senses of words induced from the context of tokens in two corpora, sense-enriched word embeddings are aligned using self-supervision and a flexible matching mechanism. This approach makes it possible to test for multiple sense-level language variations such as sense gain/presence, loss/absence and broadening/narrowing, while providing explanation of the changes through visualization of related concepts. We illustrate the utility of the method with sense- and word-level semantic shift detection results for multiple evaluation datasets in diachronic settings and dialect variation in the synchronic setting.
BibTeX
@inproceedings{arrington-etal-2025-conshift,
title = "{C}on{S}hift: Sense-based Language Variation Analysis using Flexible Alignment",
author = "Arrington, Clare and
Gruppi, Mauricio and
Adali, Sibel",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-naacl.9/",
pages = "167--181",
ISBN = "979-8-89176-195-7"
}