# Toten: A Knowledge-Based System For Structure-Preserving Representation Of Physical Quantities And Technical Notation In Brazilian Portuguese

arXiv: https://arxiv.org/abs/2606.19626 · HTML: https://mlsanity.com/paper/2606.19626/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 54 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models](https://mlsanity.com/paper/2012.15613/) (2020)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [Byte Pair Encoding is Suboptimal for Language Model Pretraining](https://mlsanity.com/paper/2004.03720/) (2020)
- [Do NLP Models Know Numbers? Probing Numeracy in Embeddings](https://mlsanity.com/paper/1909.07940/) (2019)
- [Injecting Numerical Reasoning Skills into Language Models](https://mlsanity.com/paper/2004.04487/) (2020)
- [Tokenization Is More Than Compression](https://mlsanity.com/paper/2402.18376/) (2024)
- [GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer](https://mlsanity.com/paper/2311.08526/) (2023)
- [Inductive logic programming at 30: a new introduction](https://mlsanity.com/paper/2008.07912/) (2020)
- [Representing Numbers in NLP: a Survey and a Vision](https://mlsanity.com/paper/2103.13136/) (2021)
- [Impact of Tokenization on Language Models: An Analysis for Turkish](https://mlsanity.com/paper/2204.08832/) (2022)
- [Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models](https://mlsanity.com/paper/2405.05417/) (2024)
- [Numeracy for Language Models: Evaluating and Improving their Ability to Predict Numbers](https://mlsanity.com/paper/1805.08154/) (2018)
- [Number Cookbook: Number Understanding of Language Models and How to Improve It](https://mlsanity.com/paper/2411.03766/) (2024)
- [Evaluating GPT-3.5 and GPT-4 Models on Brazilian University Admission Exams](https://mlsanity.com/paper/2303.17003/) (2023)
- [Sabi'a: Portuguese Large Language Models](https://mlsanity.com/paper/2304.07880/) (2023)
- [Tokenization is Sensitive to Language Variation](https://mlsanity.com/paper/2502.15343/) (2025)
- [CQE: A Comprehensive Quantity Extractor](https://mlsanity.com/paper/2305.08853/) (2023)

## Abstract (arXiv)

AI pipelines that reason quantitatively over technical text depend on input where physical quantities, numbers, units, and symbolic expressions arrive intact; when these entities fragment at tokenization, errors propagate downstream. Byte-Pair Encoding, optimized for vocabulary compression, is blind to such entities and fragments them into arbitrary subwords -- a problem aggravated in technical Brazilian Portuguese. We present TOTEN, a knowledge-based system whose input representation preserves each technical entity as a whole, typed unit: vocabulary is not derived statistically but classified declaratively under a formal ontology of engineering entities (OEE). The core is the triple <O, classify, {inst_tau}>: types, principles, and invariants; a classifier mapping raw text into typed regions; and instantiators yielding a self-descriptive representation. Integrity rests on deterministic coupling to three external authorities: Pint (dimensional), Unicode Character Database (typographic), and RSLP (Portuguese morphology). We evaluate four properties verifiable by construction -- atomicity, dimensional equivalence, typographic robustness, numerical reconstruction -- on an internal benchmark (EngQuant, N=800) and four Brazilian Portuguese external corpora (N=1771 eligible cases), and report detection recall. Against eight state-of-the-art baselines, TOTEN reaches unit atomicity in all contrasts and reconstruction of 0.775-0.904 externally vs. 0.627-0.703 for the best (Quantulum3); on EngQuant, 0.780 vs. 0.340. Differences are significant (McNemar, Holm-corrected). Spearman correlation between internal and external rankings confirms concurrent validity of the control benchmark. TOTEN shows statistical parity with Pint in dimensional equivalence. The result is a structurally faithful, auditable, low-cost input layer for intelligent systems on technical knowledge, without generative models.