Papers โ€บ Swap and Predict -- Predicting the Semantic Changes in Words across Corpora by Context Swapping

Swap and Predict -- Predicting the Semantic Changes in Words across Corpora by Context Swapping

16 Oct 2023arXiv:2310.10397archive 2025-07-28

Taichi Aida, Danushka Bollegala

Meanings of words change over time and across domains. Detecting the semantic changes of words is an important task for various NLP applications that must make time-sensitive predictions. We consider the problem of predicting whether a given target word, w, changes its meaning between two different text corpora, ๐’žโ‚ and ๐’žโ‚‚. For this purpose, we propose Swapping-based Semantic Change Detection (SSCD), an unsupervised method that randomly swaps contexts between ๐’žโ‚ and ๐’žโ‚‚ where w occurs. We then look at the distribution of contextualised word embeddings of w, obtained from a pretrained masked language model (MLM), representing the meaning of w in its occurrence contexts in ๐’žโ‚ and ๐’žโ‚‚. Intuitively, if the meaning of w does not change between ๐’žโ‚ and ๐’žโ‚‚, we would expect the distributions of contextualised word embeddings of w to remain the same before and after this random swapping process. Despite its simplicity, we demonstrate that even by using pretrained MLMs without any fine-tuning, our proposed context swapping method accurately predicts the semantic changes of words in four languages (English, German, Swedish, and Latin) and across different time spans (over 50 years and about five years). Moreover, our method achieves significant performance improvements compared to strong baselines for the English semantic change prediction task. Source code is available at https://github.com/a1da4/svp-swap .

PaperPDFCode

Code

a1da4/svp-swap officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Change DetectionLanguage ModellingWord Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change ยท a person checks every report against the paper or source before anything changes; decisions are listed on /corrections