Learn classifier weights from synthetic typing data

Scoring is now features x weights (Features.swift / features.py), with the
old hand-tuned values as defaults. training/ generates synthetic mixed
Chinese/English buffers from the lexicon and word lists and trains the
weights with an averaged structured perceptron over the same segmentation
DP the input method runs. On 10,000 test buffers commit-time accuracy goes
from 97.58% to 99.62%; typing-time (prefix) accuracy from 86.15% to 87.81%.

Both apps load Resources/classifier-weights.json. A parity test checks the
Swift segmentation matches the Python one on 400 fixtures.

Also fixes space after a toned syllable being scored as an extra stray tone,
which could turn short Chinese like "u4 " into English.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
2026-11-11 08:58:08 +08:00
co-authored by Claude Opus 5.5
parent 0a7242ddb3
commit 476858d841
19 changed files with 5712 additions and 225 deletions
+40
View File
@@ -0,0 +1,40 @@
#!/usr/bin/env python3
"""Writes training/parity-fixtures.json: segmentations produced by the Python core
with the current weights. The Swift tests (ParityTests) must produce the same ones,
which keeps the two implementations in sync. Re-run after changing features or weights.
"""
import json
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
from common import DATA, WEIGHTS_PATH, core, load_models # noqa: E402
from synth import Generator # noqa: E402
OUT = os.path.join(os.path.dirname(os.path.abspath(__file__)), "parity-fixtures.json")
HAND_PICKED = ["ji3hello", "hellosu3cl3", "su3cl3github", "ji3hel", "2;3", "2.5", "uvl3", "so", "up",
"u4", "183", "2024", "Hello", "don't", "mp3", "ji3emailsu3cl3", "rup wu0 wu0 fu4cp3cl3"]
def main():
lexicon, english = load_models()
clf = core.Classifier(lexicon, english, weights=core.Classifier.load_weights(WEIGHTS_PATH))
gen = Generator(os.path.join(DATA, "lexicon.txt"), os.path.join(DATA, "english-common.txt"),
os.path.join(DATA, "english-dict.txt"), seed=7)
cases = [(k, f) for k in HAND_PICKED for f in (False, True)]
while len(cases) < 400:
ex = gen.example()
if len(ex["keys"]) <= 28:
cases.append((ex["keys"], ex["finishing"]))
cases.append((gen.prefix_of(ex)["keys"], False))
fixtures = [{"keys": k, "finishing": f,
"segments": [[s, e, m] for s, e, m in clf.segment(list(k), f)]} for k, f in cases]
with open(OUT, "w", encoding="utf-8") as fh:
json.dump(fixtures, fh, ensure_ascii=False, indent=0)
print("wrote %d fixtures to %s" % (len(fixtures), OUT))
if __name__ == "__main__":
main()