duckling/Duckling/Numeral/RU/Corpus.hs

137 lines
3.4 KiB
Haskell
Raw Normal View History

-- 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.RU.Corpus
( 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smart constructor to only allow valid `(Lang, Region)` combinations * API: `Context`'s `lang` parameter has been replaced by `locale`, with optional `Region` and backward compatibility.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
import Duckling.Numeral.Types
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)
allExamples :: [Example]
allExamples = concat
[ examples (NumeralValue 0)
[ "0"
, "ноль"
, "нисколько"
]
, examples (NumeralValue 1)
[ "1"
, "один"
]
, examples (NumeralValue 2)
[ "2"
, "02"
, "два"
]
, examples (NumeralValue 3)
[ "3"
, "три"
, "03"
]
, examples (NumeralValue 4)
[ "4"
, "четыре"
, "04"
]
, examples (NumeralValue 5)
[ "пять"
, "5"
, "05"
]
, examples (NumeralValue 33)
[ "33"
, "тридцать три"
, "0033"
]
, examples (NumeralValue 11)
[ "11"
, "одиннадцать"
]
, examples (NumeralValue 14)
[ "14"
, "четырнадцать"
]
, examples (NumeralValue 16)
[ "16"
, "шестнадцать"
]
, examples (NumeralValue 17)
[ "17"
, "семнадцать"
]
, examples (NumeralValue 18)
[ "18"
, "восемнадцать"
]
, examples (NumeralValue 312)
[ "триста двенадцать"
, "312"
]
, examples (NumeralValue 444)
[ "четыреста сорок четыре"
, "444"
]
, examples (NumeralValue 525)
[ "пятьсот двадцать пять"
, "525"
]
, examples (NumeralValue 1.5)
[ "1.5"
, "полторы"
, "один с половиной"
]
, examples (NumeralValue 3.5)
[ "3.5"
, "три с половиной"
]
, examples (NumeralValue 1.1)
[ "1.1"
, "1.10"
, "01.10"
, "1 точка 1"
, "один точка один"
]
, examples (NumeralValue 0.77)
[ "0.77"
, ".77"
]
, examples (NumeralValue 100000)
[ "100000"
, "100к"
, "100К"
]
, examples (NumeralValue 3000000)
[ "3М"
, "3000К"
, "3000000"
]
, examples (NumeralValue 1200000)
[ "1200000"
, "1.2М"
, "1200К"
, ".0012Г"
]
, examples (NumeralValue (-1200000))
[ "-1200000"
, "минус 1200000"
, "-1.2М"
, "-1200К"
, "-.0012Г"
]
]