Toten: Knowledge-Based Ontological Tokenization Of Physical Quantities And Technical Notation In Brazilian Portuguese

Computer Science > Artificial Intelligence [Submitted on 17 Jun 2026] Toten: Knowledge-Based Ontological Tokenization Of Physical Quantities And Technical Notation In Brazilian Portuguese Antonio de Sousa Leitão Filho; Allan Kardec Duailibe Barros Filho; Fabrício Saul Lima; Selby Mykael Lima dos Santos; Rejani Bandeira Vieira Sousa Byte-Pair Encoding tokenization is statistically efficient for vocabulary compression, but semantically blind to structured technical entities, fragmenting physical quantities, numbers, units, and symbolic expressions into lexically arbitrary subwords. We present TOTEN, a knowledge-based ontological tokenization framework that replaces statistical derivation with declarative classification grounded in a formal ontology of engineering entities (OEE). We formalize TOTEN as the triple <O, classify, {inst_tau}>: the ontology gathers types, structural principles, composition relations, and preservable invariants; the classification function maps raw text into typed regions; and the instantiator family yields a self-descriptive structured representation. Robustness derives from deterministic coupling with three external oracles: Pint (dimensional), Unicode Character Database (typographic), and RSLP (Portuguese morphology). Intrinsic evaluation covers four properties verifiable by construction -- ontological atomicity, dimensional equivalence, typographic robustness, and numerical reconstruction -- over an internal, physically validated benchmark (EngQuant, N=800) and four Brazilian Portuguese external corpora (N=1771 eligible cases). We also report detection recall, distinguishing coverage from conditional atomicity. Against eight state-of-the-art baselines, TOTEN achieves unit ontological atomicity in all contrasts and numerical reconstruction of 0.775-0.904 on external corpora, vs. 0.627-0.703 for the best baseline (Quantulum3); on EngQuant, 0.780 vs. 0.340. Differences are statistically significant (McNemar with Holm correction). Spearman correlation between internal and external rankings confirms concurrent validity of the control benchmark. Dimensional equivalence shows statistical parity with Pint, the oracle from which the system inherits dimensional authority. Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2606.19626 [cs.AI]   (or arXiv:2606.19626v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.19626 Focus to learn more Submission history From: Antonio Leitao Filho [view email] [v1] Wed, 17 Jun 2026 22:06:41 UTC (889 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)