Metraipolis › archive › dc_e09f7273139c

ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts — arXiv:2608.24268

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.24268
License (as archived)
CC0-1.0
Archived
2026-10-18T06:18:03.827Z
SHA-256 of the archived text
b932f29ba3584b5c7caee574113028fd97c9b0f3a699ee2b3727a6bd3ab57822
Stable URL of this page
https://metraipolis.com/documento/dc_e09f7273139c

How to cite

ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts — arXiv:2608.24268 — arXiv (en), https://arxiv.org/abs/2608.24268 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e09f7273139c (Metraipolis archive dc_e09f7273139c, sha256 b932f29ba3584b5c7caee574113028fd97c9b0f3a699ee2b3727a6bd3ab57822)
BibTeX
@misc{dce09f7273139c,
  title = {ROBE: Reversed-Order-Biased-Experts for Extracting Extreme Long-tail Events from Historical Texts — arXiv:2608.24268},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.24268},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e09f7273139c; sha256 b932f29ba3584b5c7caee574113028fd97c9b0f3a699ee2b3727a6bd3ab57822},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.24268. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper proposes methods to extract over 50 types of events from a Dutch historical corpus spanning the 17th and 18th centuries. The methods we propose aim to tackle a very challenging scenario in Machine Learning: extracting the long-tail of the long-tail. Historic data from before the 19th century is in itself a niche domain not covered in the pre-training of Large Language Models, and we aim to extract events only scarcely annotated in the training data available for this domain. We propose creating expert classifiers for subgroups of the events present in the training data. We make these groupings based on similar frequency in the training data or on semantic relatedness. Experts trained on underrepresented events are assigned higher priority when predicting to avoid being dominated by frequency biases. We refer to this new way of combining classifiers, specifically tailored to protect the long-tail, as ROBE: Reversed-Order-Biased-Experts. We also propose a controlled method to create domain-specific synthetic data. Our two implementations of ROBE outperform a simple fine-tuned encoder model with a .16 increase in precision and a .05 increase in recall respectively. The best model achieves a .11 increase in f1 for a group of long-tail classes in our niche data set.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.24268 — 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 2026-10-18T06:17:29.362Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).