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 #-}
|
|
|
|
|
|
|
|
module Duckling.Time.RO.Corpus
|
2017-09-09 20:40:04 +03:00
|
|
|
( corpus
|
|
|
|
, negativeCorpus
|
|
|
|
) where
|
2017-03-08 21:33:55 +03:00
|
|
|
|
|
|
|
import Data.String
|
2017-09-09 20:40:04 +03:00
|
|
|
import Prelude
|
2017-03-08 21:33:55 +03:00
|
|
|
|
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* API: `Context`'s `lang` parameter has been replaced by `locale`, with optional `Region` and backward compatibility.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
|
2017-03-08 21:33:55 +03:00
|
|
|
import Duckling.Resolve
|
|
|
|
import Duckling.Time.Corpus
|
|
|
|
import Duckling.TimeGrain.Types hiding (add)
|
|
|
|
import Duckling.Testing.Types hiding (examples)
|
|
|
|
|
2017-09-09 20:40:04 +03:00
|
|
|
negativeCorpus :: NegativeCorpus
|
|
|
|
negativeCorpus = (testContext, examples)
|
|
|
|
where
|
|
|
|
examples =
|
|
|
|
[ "sa"
|
|
|
|
]
|
|
|
|
|
2017-03-08 21:33:55 +03:00
|
|
|
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 RO Nothing}, allExamples)
|
2017-03-08 21:33:55 +03:00
|
|
|
|
|
|
|
allExamples :: [Example]
|
|
|
|
allExamples = concat
|
|
|
|
[ examples (datetime (2013, 2, 12, 4, 30, 0) Second)
|
|
|
|
[ "acum"
|
|
|
|
, "chiar acum"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 12, 0, 0, 0) Day)
|
|
|
|
[ "azi"
|
|
|
|
, "astazi"
|
|
|
|
, "astăzi"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 11, 0, 0, 0) Day)
|
|
|
|
[ "ieri"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 13, 0, 0, 0) Day)
|
|
|
|
[ "maine"
|
|
|
|
, "mâine"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 18, 0, 0, 0) Day)
|
|
|
|
[ "luni"
|
|
|
|
, "lunea asta"
|
|
|
|
, "lunea aceasta"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 18, 0, 0, 0) Day)
|
|
|
|
[ "Luni, 18 Feb"
|
|
|
|
, "Luni, 18 Februarie"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 19, 0, 0, 0) Day)
|
|
|
|
[ "marti"
|
|
|
|
, "marți"
|
|
|
|
, "Marti 19"
|
|
|
|
, "Marti pe 19"
|
|
|
|
, "Marți 19"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 14, 0, 0, 0) Day)
|
|
|
|
[ "joi"
|
|
|
|
, "jo"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 15, 0, 0, 0) Day)
|
|
|
|
[ "vineri"
|
|
|
|
, "vi"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 16, 0, 0, 0) Day)
|
|
|
|
[ "sambata"
|
|
|
|
, "sâmbătă"
|
|
|
|
, "sam"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 2, 17, 0, 0, 0) Day)
|
|
|
|
[ "duminica"
|
|
|
|
, "duminică"
|
|
|
|
, "du"
|
|
|
|
, "dum"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 3, 1, 0, 0, 0) Day)
|
|
|
|
[ "1 martie"
|
|
|
|
, "intai martie"
|
|
|
|
]
|
|
|
|
, examples (datetimeInterval ((2013, 6, 19, 0, 0, 0), (2013, 6, 21, 0, 0, 0)) Day)
|
|
|
|
[ "iunie 19-20"
|
|
|
|
]
|
|
|
|
, examples (datetime (2013, 12, 25, 0, 0, 0) Day)
|
|
|
|
[ "ziua de craciun"
|
|
|
|
, "crăciun"
|
|
|
|
]
|
|
|
|
]
|