Metraipolis › archive › dc_35b45f66b684

ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels — arXiv:2608.03507

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03507
License (as archived)
CC0-1.0
Archived
2026-10-31T12:19:25.421Z
SHA-256 of the archived text
a6a7ff1d0b5b41e69c4488b0fab57eb0b0acd70de5d2d0877fe6eca620361b3d
Stable URL of this page
https://metraipolis.com/documento/dc_35b45f66b684

How to cite

ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels — arXiv:2608.03507 — arXiv (en), https://arxiv.org/abs/2608.03507 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35b45f66b684 (Metraipolis archive dc_35b45f66b684, sha256 a6a7ff1d0b5b41e69c4488b0fab57eb0b0acd70de5d2d0877fe6eca620361b3d)
BibTeX
@misc{dc35b45f66b684,
  title = {ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels — arXiv:2608.03507},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03507},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35b45f66b684; sha256 a6a7ff1d0b5b41e69c4488b0fab57eb0b0acd70de5d2d0877fe6eca620361b3d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03507. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Historical language change affects morphology, syntax, semantics, and pragmatics, yet computational studies typically examine these levels with incompatible representations and therefore cannot determine whether they evolve together across languages. We address this problem by asking how the magnitude and direction of change vary across linguistic levels, languages, and historical periods within a single analytical space. We introduce ChronoLens, a framework that combines frozen multilingual language models, feature-aligned crosscoders, and post-hoc linguistic interventions, and apply it to 44.98 million documents and approximately 17.2 billion tokens from five parliamentary traditions spanning 1803--2026. The resulting sparse representations agree substantially more strongly with linguistic statistics than dense embeddings or a pooled sparse autoencoder ($\rho=0.72$ versus $0.29$ and $0.28$), and reveal that morphology, syntax, semantics, and pragmatics generally change by comparable amounts within a language, while languages differ markedly in when, how far, and in which direction they change. These findings show that historical language change is a structured, multidimensional process: similar magnitudes can conceal different trajectories, and meaningful cross-linguistic comparison requires measuring both distance and direction.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03507 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T12:05:53.054Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).