Metraipolis › archive › dc_09fbb9691516
Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages — arXiv:2609.00998
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.00998
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:33:49.916Z
- SHA-256 of the archived text
765d579e1f6476a1cac12976956fa4e203f130e65d0da293959e8717e807b3d7- Stable URL of this page
https://metraipolis.com/documento/dc_09fbb9691516
How to cite
Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages — arXiv:2609.00998 — arXiv (en), https://arxiv.org/abs/2609.00998 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_09fbb9691516 (Metraipolis archive dc_09fbb9691516, sha256 765d579e1f6476a1cac12976956fa4e203f130e65d0da293959e8717e807b3d7)
BibTeX
@misc{dc09fbb9691516,
title = {Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages — arXiv:2609.00998},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.00998},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_09fbb9691516; sha256 765d579e1f6476a1cac12976956fa4e203f130e65d0da293959e8717e807b3d7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00998. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping in the source language (Navigli, 2026). These assumptions break down for most historical and low-resource languages, whose dedicated WordNets are either incomplete or still under construction. We present Inspicio, an open-vocabulary retrieval pipeline that links tokens in context to synsets of the Open English WordNet (McCrae et al., 2020) without requiring any source-language inventory or mapping. For each occurrence, an instruction-tuned LLM produces two English translations of the surrounding sentence, a small set of candidate dictionary-style definitions, and a few candidate English lemmas. These outputs drive a hybrid retrieval step that combines dense definition-synset similarity, sparse lemma matching, and Maximal Marginal Relevance re-ranking. We evaluate the pipeline across a 6x6 grid of LLMs and sentence-embedding models on a new bilingual set of manually annotated Latin and Ancient Greek perception verbs, on a subset of PREMOVE dataset (Farina, 2025), and on a diachronic sample of Italian. The best configuration reaches 96% Recall@50 on the perception-verb test set, with each component contributing measurable gains, and remains competitive in the out-of-domain and cross-lingual settings. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.00998 — 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 2026-10-17T06:15:12.846Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).