Eval report — step-001800
- entries evaluated: 4535
- full-parseaddress parsingThe process of decomposing a free-text postal address string into structured components — house number, street name, locality, region, postcode, and country — so a geocoder can resolve them to coordinates. exact matchexact matchThe share of eval items whose every component is correct (compared per-span or per-token). Stricter than per-tag F1, which credits partial correctness.: 0.1074
- mean tokentokenOne word or subword in the tokenized input. For the neural classifier, tokens come from SentencePiece (subword units); for the rule classifiers, tokens are whitespace- and punctuation-separated words. confidence: 0.8566
Per-component F1
| tag | precisionprecisionOf the spans the model labeled as a given tag, the fraction it got right. High precision means few false positives. Paired with recall to compute F1. | recallrecallOf the spans whose gold label is a given tag, the fraction the model found. High recall means few misses. Paired with precision to compute F1. | f1 | support |
|---|---|---|---|---|
| countrycountryThe top-level address component (an ISO country). Closed-vocabulary, so it is best handled by a deterministic matcher feeding a proposal rather than a retrained model head. | 0.2955 | 0.2653 | 0.2796 | 245 |
| regionregionThe first-level administrative subdivision of a country — a US state, a French region, a province. The component between country and locality. | 0.4411 | 0.1098 | 0.1759 | 3205 |
| localitylocalityThe city / town / settlement component of an address: a populated place sitting between region and neighbourhood in the hierarchy. | 0.2330 | 0.3089 | 0.2657 | 3357 |
| dependent_locality | 0.0000 | 0.0000 | 0.0000 | 40 |
| postcodepostcodeThe country-specific postal code (US ZIP, French code postal, etc.). Mailwoman handles postcode parsing entirely by rule classifier — a regex problem, not an ML one. | 0.8426 | 0.6846 | 0.7554 | 2980 |
| subregion | 0.0000 | 0.0000 | 0.0000 | 0 |
| cedexCEDEX (Courrier d'Entreprise à Distribution Exceptionnelle). A French postal routing for high-volume business mail: a CEDEX code delivers directly from a sorting centre, bypassing the local post office. A common negative-space format Mailwoman must parse. | 0.0000 | 0.0000 | 0.0000 | 1 |
| venuevenueA named, non-address place — a business, building, park, or stadium. Mailwoman's free-text point-of-interest component, added as a Tier 2 fine label. | 0.3862 | 0.4024 | 0.3941 | 1101 |
| streetstreetThe named linear feature along which house numbers are ordered. Decomposes into a name plus street affixes; one of the Tier 2 fine labels. | 0.3326 | 0.2217 | 0.2660 | 2928 |
| house_number | 0.7316 | 0.8433 | 0.7835 | 1742 |
Calibration (confidence bucket → accuracy)
| bucket | n | accuracy |
|---|---|---|
| 0.0–0.1 | 0 | 0.0000 |
| 0.1–0.2 | 19 | 0.5789 |
| 0.2–0.3 | 316 | 0.3323 |
| 0.3–0.4 | 1213 | 0.3776 |
| 0.4–0.5 | 2754 | 0.3413 |
| 0.5–0.6 | 3647 | 0.3548 |
| 0.6–0.7 | 3659 | 0.3884 |
| 0.7–0.8 | 4610 | 0.4063 |
| 0.8–0.9 | 7716 | 0.4396 |
| 0.9–1.0 | 37314 | 0.5988 |