2017-03-08 21:33:55 +03:00
|
|
|
|
-- 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 #-}
|
|
|
|
|
|
2017-03-16 23:42:15 +03:00
|
|
|
|
module Duckling.Numeral.RU.Corpus
|
2017-03-08 21:33:55 +03:00
|
|
|
|
( corpus ) where
|
|
|
|
|
|
|
|
|
|
import Prelude
|
|
|
|
|
import Data.String
|
|
|
|
|
|
Locales support
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* API: `Context`'s `lang` parameter has been replaced by `locale`, with optional `Region` and backward compatibility.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
2017-10-13 18:15:32 +03:00
|
|
|
|
import Duckling.Locale
|
2017-03-16 23:42:15 +03:00
|
|
|
|
import Duckling.Numeral.Types
|
2017-03-08 21:33:55 +03:00
|
|
|
|
import Duckling.Resolve
|
|
|
|
|
import Duckling.Testing.Types
|
|
|
|
|
|
|
|
|
|
corpus :: Corpus
|
Locales support
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
2017-10-13 18:15:32 +03:00
|
|
|
|
corpus = (testContext {locale = makeLocale RU Nothing}, allExamples)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
|
|
|
|
|
allExamples :: [Example]
|
|
|
|
|
allExamples = concat
|
2017-03-16 23:42:15 +03:00
|
|
|
|
[ examples (NumeralValue 0)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "0"
|
|
|
|
|
, "ноль"
|
2017-10-24 20:27:59 +03:00
|
|
|
|
, "нисколько"
|
2017-03-08 21:33:55 +03:00
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 1)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "1"
|
|
|
|
|
, "один"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 2)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "2"
|
|
|
|
|
, "02"
|
|
|
|
|
, "два"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 3)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "3"
|
|
|
|
|
, "три"
|
|
|
|
|
, "03"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 4)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "4"
|
|
|
|
|
, "четыре"
|
|
|
|
|
, "04"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 5)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "пять"
|
|
|
|
|
, "5"
|
|
|
|
|
, "05"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 33)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "33"
|
|
|
|
|
, "тридцать три"
|
|
|
|
|
, "0033"
|
|
|
|
|
]
|
2017-10-24 20:27:59 +03:00
|
|
|
|
, examples (NumeralValue 11)
|
|
|
|
|
[ "11"
|
|
|
|
|
, "одиннадцать"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 14)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "14"
|
|
|
|
|
, "четырнадцать"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 16)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "16"
|
|
|
|
|
, "шестнадцать"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 17)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "17"
|
|
|
|
|
, "семнадцать"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 18)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "18"
|
|
|
|
|
, "восемнадцать"
|
|
|
|
|
]
|
2017-10-24 20:27:59 +03:00
|
|
|
|
, examples (NumeralValue 312)
|
|
|
|
|
[ "триста двенадцать"
|
|
|
|
|
, "312"
|
|
|
|
|
]
|
|
|
|
|
, examples (NumeralValue 444)
|
|
|
|
|
[ "четыреста сорок четыре"
|
|
|
|
|
, "444"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 525)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "пятьсот двадцать пять"
|
|
|
|
|
, "525"
|
|
|
|
|
]
|
2017-10-24 20:27:59 +03:00
|
|
|
|
, examples (NumeralValue 1.5)
|
|
|
|
|
[ "1.5"
|
|
|
|
|
, "полторы"
|
2017-11-15 21:41:33 +03:00
|
|
|
|
, "один с половиной"
|
|
|
|
|
]
|
|
|
|
|
, examples (NumeralValue 3.5)
|
|
|
|
|
[ "3.5"
|
|
|
|
|
, "три с половиной"
|
2017-10-24 20:27:59 +03:00
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 1.1)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "1.1"
|
|
|
|
|
, "1.10"
|
|
|
|
|
, "01.10"
|
|
|
|
|
, "1 точка 1"
|
|
|
|
|
, "один точка один"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 0.77)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "0.77"
|
|
|
|
|
, ".77"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 100000)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "100000"
|
|
|
|
|
, "100к"
|
|
|
|
|
, "100К"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 3000000)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "3М"
|
|
|
|
|
, "3000К"
|
|
|
|
|
, "3000000"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue 1200000)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "1200000"
|
|
|
|
|
, "1.2М"
|
|
|
|
|
, "1200К"
|
|
|
|
|
, ".0012Г"
|
|
|
|
|
]
|
2017-03-16 23:42:15 +03:00
|
|
|
|
, examples (NumeralValue (-1200000))
|
2017-03-08 21:33:55 +03:00
|
|
|
|
[ "-1200000"
|
|
|
|
|
, "минус 1200000"
|
|
|
|
|
, "-1.2М"
|
|
|
|
|
, "-1200К"
|
|
|
|
|
, "-.0012Г"
|
|
|
|
|
]
|
|
|
|
|
]
|