kami
29329b5f0e
The clarify gate thinned any one-word utterance to 0.3 confidence, which
trips the stage-3 gate and comes back as "не совсем поняла". That is an
English intuition. Russian packs subject, tense and gender into one word,
so "поужинал" is a complete report and "привет" a complete greeting, and
both got clarified.
thinSingleToken keeps the rule for bare nominals, where it is real ("вода"
is a fact-or-query coin flip), and spares two classes: a closed lexicon of
social and control singles, and any token carrying a verb ending. Both
tests are offline.
Fixture: false clarifies 3 → 2, intent-only 74.0% → 75.3%, full accuracy
unchanged at 70.1%, missed clarify still 1.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TrVSBKe3RFDF4fGYKWYQnX
91 lines
3.9 KiB
Go
91 lines
3.9 KiB
Go
package router
|
|
|
|
import "strings"
|
|
|
|
// thinSingleToken — is a one-word utterance thin evidence, or is it a whole
|
|
// sentence?
|
|
//
|
|
// The rule this replaces was `len(strings.Fields(u)) <= 1`, an English
|
|
// intuition. It does not transfer: Russian packs a subject, a tense and a
|
|
// gender into one word, so "поужинал" is a complete report and "привет" a
|
|
// complete greeting, yet both got thinned and came back as "не совсем поняла".
|
|
// Meanwhile the case the rule exists for is real — a bare noun like "вода" or
|
|
// "бэкап" genuinely does not say fact-vs-query or act-vs-report.
|
|
//
|
|
// So: still one token, but only thin it when the token is a bare nominal.
|
|
// Two escapes, both cheap and both offline:
|
|
//
|
|
// - a closed lexicon of social and command singles, which are complete by
|
|
// definition ("привет", "спасибо", "стоп", "yes");
|
|
// - a suffix test for an inflected predicate — past tense, 2nd person,
|
|
// reflexive. Verbs carry their own subject, so a verb IS a sentence.
|
|
//
|
|
// The suffix test is deliberately loose about nouns that happen to end the
|
|
// same way ("канал" reads as past tense here). That direction of error only
|
|
// costs a clarify we would not have asked for; the other direction — treating
|
|
// a real report as thin — is the bug being fixed.
|
|
func thinSingleToken(utterance string) bool {
|
|
f := strings.Fields(utterance)
|
|
if len(f) != 1 {
|
|
return false
|
|
}
|
|
w := strings.ToLower(strings.Trim(f[0], ".,!?;:—-\"'«»()"))
|
|
if w == "" {
|
|
return false
|
|
}
|
|
if completeSingles[w] {
|
|
return false
|
|
}
|
|
return !looksInflected(w)
|
|
}
|
|
|
|
// completeSingles — one-word utterances that need no second half. Greetings,
|
|
// acknowledgements and the control words a voice loop has to honour instantly.
|
|
var completeSingles = map[string]bool{
|
|
// ru: social
|
|
"привет": true, "здравствуй": true, "здравствуйте": true, "здорово": true,
|
|
"пока": true, "прощай": true, "спокойной": true, "спасибо": true,
|
|
"благодарю": true, "извини": true, "прости": true, "пожалуйста": true,
|
|
"да": true, "нет": true, "ага": true, "угу": true, "ок": true, "окей": true,
|
|
"хорошо": true, "ладно": true, "конечно": true, "верно": true, "точно": true,
|
|
// ru: control
|
|
"стоп": true, "отмена": true, "отбой": true, "хватит": true, "тихо": true,
|
|
"повтори": true, "продолжай": true, "помоги": true, "помощь": true,
|
|
// en
|
|
"hi": true, "hello": true, "hey": true, "bye": true, "goodbye": true,
|
|
"thanks": true, "thank": true, "sorry": true, "please": true,
|
|
"yes": true, "no": true, "yep": true, "nope": true, "ok": true, "okay": true,
|
|
"sure": true, "right": true, "stop": true, "cancel": true, "help": true,
|
|
"repeat": true, "continue": true,
|
|
}
|
|
|
|
// inflectedSuffixes — endings that mark a finite or past-tense Russian verb.
|
|
// Ordered longest-first is unnecessary (any match wins), but each entry is
|
|
// chosen to be long enough that common nouns rarely collide.
|
|
var inflectedSuffixes = []string{
|
|
// reflexive — strongly verbal whatever precedes it
|
|
"ся", "сь",
|
|
// past tense
|
|
"ал", "ял", "ил", "ел", "ыл", "ул", "ёл", "ала", "яла", "ила", "ела",
|
|
"ыла", "ула", "али", "яли", "или", "ели",
|
|
// 2nd person singular
|
|
"ешь", "ишь", "ёшь",
|
|
// 1st/2nd person plural, 3rd person plural
|
|
"аем", "яем", "уем", "аете", "ите", "ают", "яют", "уют", "ат", "ят",
|
|
}
|
|
|
|
// looksInflected — does the word carry a verb ending? Short words are exempt:
|
|
// a three-letter token is not enough stem to trust a two-letter suffix on
|
|
// ("газ" would otherwise never match, but "нос" and "лес" would).
|
|
func looksInflected(w string) bool {
|
|
if len([]rune(w)) < 5 {
|
|
return false
|
|
}
|
|
for _, s := range inflectedSuffixes {
|
|
if strings.HasSuffix(w, s) {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|