2017-05-23 20:32:00 +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.Distance.TR.Corpus
|
|
|
|
( corpus ) where
|
|
|
|
|
|
|
|
import Data.String
|
|
|
|
import Prelude
|
|
|
|
|
|
|
|
import Duckling.Distance.Types
|
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* API: `Context`'s `lang` parameter has been replaced by `locale`, with optional `Region` and backward compatibility.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
|
2017-05-23 20:32:00 +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 TR Nothing}, allExamples)
|
2017-05-23 20:32:00 +03:00
|
|
|
|
|
|
|
allExamples :: [Example]
|
|
|
|
allExamples = concat
|
2018-02-10 03:12:48 +03:00
|
|
|
[ examples (simple Kilometre 3)
|
2017-05-23 20:32:00 +03:00
|
|
|
[ "3 Kilometre"
|
|
|
|
, "3 kilometre"
|
|
|
|
, "3 km"
|
|
|
|
, "3km"
|
|
|
|
]
|
2018-02-10 03:12:48 +03:00
|
|
|
, examples (simple Kilometre 3.0)
|
2017-05-24 18:46:26 +03:00
|
|
|
[ "3,0 km"
|
2017-05-23 20:32:00 +03:00
|
|
|
]
|
2018-02-10 03:12:48 +03:00
|
|
|
, examples (simple Mile 8)
|
2017-05-23 20:32:00 +03:00
|
|
|
[ "8 Mil"
|
|
|
|
, "8 mil"
|
|
|
|
]
|
2018-02-10 03:12:48 +03:00
|
|
|
, examples (simple Metre 9)
|
2017-05-23 20:32:00 +03:00
|
|
|
[ "9 Metre"
|
|
|
|
, "9 metre"
|
|
|
|
, "9 m"
|
|
|
|
, "9m"
|
|
|
|
]
|
2018-02-10 03:12:48 +03:00
|
|
|
, examples (simple Centimetre 2)
|
2017-05-23 20:32:00 +03:00
|
|
|
[ "2 Santimetre"
|
|
|
|
, "2 santim"
|
|
|
|
, "2 cm"
|
|
|
|
, "2cm"
|
|
|
|
]
|
|
|
|
]
|