Tag: language
-
Portfolio ·
The Language Layer
Stateful templates with stateless slots — sentence shapes filled from the live state of the world. Approximately seven thousand distinct utterances from the current wordbook, a floor that grows as vocabulary is harvested. The mixture-of-experts layer in development.
-
Portfolio ·
A Deterministic English Fluency Layer
A ~50 KB cabinet of rule-based specialists that turn a typed semantic trace into fluent English. No neural network, no training, no GPU. Inflection, lemmatisation with etymological layering, article selection, verb conjugation. 104/104 tests pass. A reference implementation for the separation of semantic navigation and surface rendering.
-
Portfolio ·
Etymological Layering in English Lemmatisation
English is three morphological systems pretending to be one — Germanic inflection, partly-productive Latin derivation, Greek compound roots, French borrowings. A vocabulary-gated collapse rule per layer handles all four correctly; a single uniform rule cannot. The layer distribution of a text also turns out to be a cheap stylometric feature.
-
Portfolio ·
Post-Hoc Morphology Correction for Quantised LLMs
Quantised and distilled language models lose irregular morphology first — 'runned', 'childs', 'mouses' — because the irregulars are carried by a smaller fraction of parameters. A 450-entry irregulars table plus a short repair function catches and corrects these without retraining, without latency cost, and without touching the model. Closed-form failures should not be solved by statistical learners.
-
Portfolio ·
Floor 9 — Word2Vec: The Field Touches the Manifold and Flinches
In 2013, language became geometric for the first time at industrial scale. The vectors were real. The manifold under them was never quite named.
-
Portfolio ·
Floor 10 — Transformers: The Brilliant Architecture With the Wrong Output
The most impressive machine learning architecture ever built has a continuous heart and a one-hot mouth. Nothing wrong with the heart.