Why Japanese addresses break Western parsers
Japanese addresses run backwards: prefecture, then city, then block, then number. They have no street names. Wepulled 6,373 of them from Who's On First.
16 posts tagged with "Model training"
Training runs, loss recipes, verdict smokes, and divergence diagnostics.
View All TagsPO Box Boîte Postale Apartado: Stage 3 ships with 6 new tags
v0.6.0 expands the schema from 10 to 16 component tags. PO box recognition: 0% → 51.9% in one training run.
Five tries, same failure — narrowing v0.5.0's training problem by elimination
This is a follow-up to yesterday's post about the v0.5.0 C-train failures. Yesterday we ran four attempts and ruled out three suspects. Today we ran a fifth and ruled out a fourth. One hypothesis remains. The method we used comes directly from software debugging, so this post is written for engineers who haven't run a training campaign before.
Two voices arguing inside a model — a beginner-friendly debugging story
Mailwoman is an open-source address parser that runs in Node and the browser. It uses a small neural model to label address components ("350" = house number, "NY" = region, etc.). Try the live demo.
Four training runs, zero shipped weights — bisecting v0.5.0's divergence
Mailwoman is an open-source address parser. This post is a training log entry from May 2026 documenting the v0.5.0 divergence investigation. For current project status, see what ships today.
Five training runs, one shipped checkpoint — what we learned from v0.4.0
Mailwoman is an open-source address parser. This post is a historical retrospective on the v0.4.0 training campaign (May 2026). For current project status, see what ships today.