Skip to main content

One post tagged with "Stage 3 (extended schema)"

Articles about Knowledge Ladder Stage 3 — the 33-label extended schema (PO box, unit, street affixes, intersections).

View All Tags

PO Box Boîte Postale Apartado: Stage 3 ships with 6 new tags

· 6 min read
Teffen Ellis
Sister Software

For its first six versions, Mailwoman emitted ten BIO tags. The model could pick street out of a row but not street_prefix, street_suffix, unit, or po_box. Real addresses are messier than that. The golden eval set has known examples — 6220 SE Salmon St, Portland, OR 97215 (Stage 2 collapses prefix+name+suffix), 123 Main St Apt 4B, Springfield, IL 62701 (loses the apartment), PO Box 123, Burlington, VT 05401 (treats it as a malformed street).

v0.6.0 adds six tags: street_prefix, street_suffix, unit, po_box, intersection_a, intersection_b. The model is the same h384/6L/6H transformer. The recipe is the same v0.5.1 settings. The tokenizer is the same v0.6.0-a0 multi-script bundle. The only structural change is the output head: 21 BIO labels → 33.