mirror of
https://github.com/facebook/duckling.git
synced 2024-12-01 08:19:36 +03:00
ab0ad0256e
Summary: * Locales support for the library, following `<Lang>_<Region>` with ISO 639-1 code for `<Lang>` and ISO 3166-1 alpha-2 code for `<Region>` (#33) * `Locale` opaque type (composite of `Lang` and `Region`) with `makeLocale` smart constructor to only allow valid `(Lang, Region)` combinations * API: `Context`'s `lang` parameter has been replaced by `locale`, with optional `Region` and backward compatibility. * `Rules/<Lang>.hs` exposes - `langRules`: cross-locale rules for `<Lang>`, from `<Dimension>/<Lang>/Rules.hs` - `localeRules`: locale-specific rules, from `<Dimension>/<Lang>/<Region>/Rules.hs` - `defaultRules`: `langRules` + specific rules from select locales to ensure backward-compatibility * Corpus, tests & classifiers - 1 classifier per locale, with default classifier (`<Lang>_XX`) when no locale provided (backward-compatible) - Default classifiers are built on existing corpus - Locale classifiers are built on - `<Dimension>/<Lang>/Corpus.hs` exposes a common `corpus` to all locales of `<Lang>` - `<Dimension>/<Lang>/<Region>/Corpus.hs` exposes `allExamples`: a list of examples specific to the locale (following `<Dimension>/<Lang>/<Region>/Rules.hs`). - Locale classifiers use the language corpus extended with the locale examples as training set. - Locale examples need to use the same `Context` (i.e. reference time) as the language corpus. - For backward compatibility, `<Dimension>/<Lang>/Corpus.hs` can expose also `defaultCorpus`, which is `corpus` augmented with specific examples. This is controlled by `getDefaultCorpusForLang` in `Duckling.Ranking.Generate`. - Tests run against each classifier to make sure runtime works as expected. * MM/DD (en_US) vs DD/MM (en_GB) example to illustrate Reviewed By: JonCoens, blandinw Differential Revision: D6038096 fbshipit-source-id: f29c28d
156 lines
3.5 KiB
Haskell
156 lines
3.5 KiB
Haskell
-- Copyright (c) 2016-present, Facebook, Inc.
|
|
-- All rights reserved.
|
|
--
|
|
-- This source code is licensed under the BSD-style license found in the
|
|
-- LICENSE file in the root directory of this source tree. An additional grant
|
|
-- of patent rights can be found in the PATENTS file in the same directory.
|
|
|
|
|
|
{-# LANGUAGE OverloadedStrings #-}
|
|
|
|
module Duckling.Numeral.IT.Corpus
|
|
( corpus ) where
|
|
|
|
import Prelude
|
|
import Data.String
|
|
|
|
import Duckling.Locale
|
|
import Duckling.Numeral.Types
|
|
import Duckling.Resolve
|
|
import Duckling.Testing.Types
|
|
|
|
corpus :: Corpus
|
|
corpus = (testContext {locale = makeLocale IT Nothing}, allExamples)
|
|
|
|
allExamples :: [Example]
|
|
allExamples = concat
|
|
[ examples (NumeralValue 0)
|
|
[ "0"
|
|
, "nulla"
|
|
, "zero"
|
|
]
|
|
, examples (NumeralValue 1)
|
|
[ "1"
|
|
, "uno"
|
|
, "Un"
|
|
]
|
|
, examples (NumeralValue 2)
|
|
[ "2"
|
|
, "due"
|
|
]
|
|
, examples (NumeralValue 3)
|
|
[ "3"
|
|
, "tre"
|
|
]
|
|
, examples (NumeralValue 4)
|
|
[ "4"
|
|
, "quattro"
|
|
]
|
|
, examples (NumeralValue 5)
|
|
[ "5"
|
|
, "cinque"
|
|
]
|
|
, examples (NumeralValue 6)
|
|
[ "6"
|
|
, "sei"
|
|
]
|
|
, examples (NumeralValue 7)
|
|
[ "7"
|
|
, "sette"
|
|
]
|
|
, examples (NumeralValue 8)
|
|
[ "8"
|
|
, "otto"
|
|
]
|
|
, examples (NumeralValue 9)
|
|
[ "9"
|
|
, "nove"
|
|
]
|
|
, examples (NumeralValue 10)
|
|
[ "10"
|
|
, "dieci"
|
|
]
|
|
, examples (NumeralValue 33)
|
|
[ "33"
|
|
, "trentatré"
|
|
, "0033"
|
|
]
|
|
, examples (NumeralValue 11)
|
|
[ "11"
|
|
, "Undici"
|
|
]
|
|
, examples (NumeralValue 12)
|
|
[ "12"
|
|
, "dodici"
|
|
]
|
|
, examples (NumeralValue 13)
|
|
[ "13"
|
|
, "tredici"
|
|
]
|
|
, examples (NumeralValue 14)
|
|
[ "14"
|
|
, "quattordici"
|
|
]
|
|
, examples (NumeralValue 15)
|
|
[ "15"
|
|
, "quindici"
|
|
]
|
|
, examples (NumeralValue 16)
|
|
[ "16"
|
|
, "sedici"
|
|
]
|
|
, examples (NumeralValue 17)
|
|
[ "17"
|
|
, "diciassette"
|
|
]
|
|
, examples (NumeralValue 18)
|
|
[ "18"
|
|
, "diciotto"
|
|
]
|
|
, examples (NumeralValue 19)
|
|
[ "19"
|
|
, "diciannove"
|
|
]
|
|
, examples (NumeralValue 20)
|
|
[ "20"
|
|
, "venti"
|
|
]
|
|
, examples (NumeralValue 1.1)
|
|
[ "1,1"
|
|
, "1,10"
|
|
, "01,10"
|
|
]
|
|
, examples (NumeralValue 0.77)
|
|
[ "0,77"
|
|
, ",77"
|
|
]
|
|
, examples (NumeralValue 100000)
|
|
[ "100.000"
|
|
, "100000"
|
|
, "100K"
|
|
, "100k"
|
|
]
|
|
, examples (NumeralValue 3000000)
|
|
[ "3M"
|
|
, "3000K"
|
|
, "3000000"
|
|
, "3.000.000"
|
|
]
|
|
, examples (NumeralValue 1200000)
|
|
[ "1.200.000"
|
|
, "1200000"
|
|
, "1,2M"
|
|
, "1200K"
|
|
, ",0012G"
|
|
]
|
|
, examples (NumeralValue (-1200000))
|
|
[ "- 1.200.000"
|
|
, "-1200000"
|
|
, "meno 1.200.000"
|
|
, "negativo 1200000"
|
|
, "-1,2M"
|
|
, "-1200K"
|
|
, "-,0012G"
|
|
]
|
|
]
|