AsoSoft Library offers basic natural language processing (NLP) algorithms for the Kurdish Language (ckb: Central branch of Kurdish). AsoSoft Library is written in C#.
- Grapheme-to-Phoneme (G2P) converter and Transliteration: converts Kurdish text into syllabified phoneme string. Also transliterates Kurdish texts from Arabic script into Latin script and vice versa.
- Normalizer: normalizes the Kurdish text and punctuation marks, unifies numerals, replaces Html Entities, extracts and replaces URLs and emails, and more.
- Numeral Converter: converts any type of numbers into Kurdish words.
- Sort: Sorts a list in correct Kurdish alphabet order.
- Poem Meter Classifier: Classifies the meter of the input Kurdish poem
This function is based on the study "Automated Grapheme-to-Phoneme Conversion for Central Kurdish based on Optimality Theory".
Converts Central Kurdish text in standard Arabic script into syllabified phonemic Latin script (i.e. graphemes to phonems)
General format:
AsoSoft.G2P(string text,
bool convertNumbersToWord = false,
bool backMergeConjunction = true,
bool singleOutputPerWord = true);
An example:
AsoSoft.G2P("شەو و ڕۆژ بووین بە گرفت. درێژیی دیوارەکەی گرتن");
>ˈşeˈwû ˈřoj ˈbûyn ˈbe ˈgiˈrift. ˈdiˈrêˈjîy ˈdîˈwaˈreˈkey ˈgirˈtin<
Arabic script into Hawar Latin script (حغڕڵ→ḧẍřł):
AsoSoft.Ar2La("گیرۆدەی خاڵی ڕەشتە؛ گوێت لە نەغمەی تویوورە؟");
>gîrodey xałî řeşte; gwêt le neẍmey tuyûre?<
Arabic script into simplified (حغڕڵ→hxrl) Hawar Latin script:
AsoSoft.Ar2LaSimple("گیرۆدەی خاڵی ڕەشتە؛ گوێت لە نەغمەی تویوورە؟");
>gîrodey xalî reşte; gwêt le nexmey tuyûre?<
Latin script (Hawar) into Arabic script:
AsoSoft.La2Ar("Gelî keç û xortên kurdan, hûn hemû bi xêr biçin");
>گەلی کەچ و خۆرتێن کوردان، هوون هەموو ب خێر بچن<
Arabic script into IPA:
AsoSoft.Phonemes2IPA(AsoSoft.G2P("شەو و ڕۆژ بووین بە گرفت. درێژیی دیوارەکە گرتن"));
>ʃa·wu ro̞ʒ bujn ba gɪ·ɾɪft. dɪ·ɾɛ·ʒij di·wä·ɾa·ka gɪɾ·tɪn<
Several functions needed for Central Kurdish text normalization:
Two character replacement lists are provided as the resources of the library:
- Deep Unicode Corrections:
- replacing deprecated Arabic Presentation Forms (FB50–FDFF and FE70–FEFF) with corresponding standard characters.
- replacing different types of dashes and spaces
- removing Unicode control character
- Additional Unicode Corrections
- replacing special Arabic math signs with corresponding Latin characters
- replacing similar, but different letters with standard characters (e.g. ڪ,ے,ٶ with ک,ی,ؤ)
The normalization task in this function:
- for all Arabic scripts (including Kurdish, Arabic, and Persian):
- Character-based replacement:
- Above mentioned replacement lists
- Private Use Area (U+E000 to U+F8FF) with White Square character
- Character-based replacement:
- Standardizing and removing duplicated or unnecessary Zero-Width characters
- removing unnecessary Tatweels (U+0640)
- only for Central Kurdish:
- standardizing Kurdish characters: ە, هـ, ی, and ک
- correcting miss-converted characters from non-Unicode fonts
- replacing word-initial ر with ڕ
the simple overloading:
AsoSoft.Normalize("دەقے شیَعري خـــۆش. رهنگهكاني خاك");
>دەقی شێعری خۆش. ڕەنگەکانی خاک<
or the complete overloading:
AsoSoft.Normalize(string text,
bool isOnlyKurdish,
bool changeInitialR,
bool deepUnicodeCorrectios,
bool additionalUnicodeCorrections,
Dictionary<char, string> usersReplaceList);
AliK2Unicode
converts Kurdish text written in AliK fonts (developed by Abas Majid in 1997) into Unicode standard. Ali-K fonts: Alwand, Azzam, Hasan, Jiddah, kanaqen, Khalid, Sahifa, Sahifa Bold, Samik, Sayid, Sharif, Shrif Bold, Sulaimania, Traditional
AsoSoft.AliK2Unicode("ئاشناكردنى خويَندكار بة طوَرِانكاريية كوَمةلاَيةتييةكان");
>ئاشناکردنی خوێندکار بە گۆڕانکارییە کۆمەڵایەتییەکان<
AliWeb2Unicode
converts Kurdish text written in AliK fonts into Unicode standard. Ali-Web fonts: Malper, Malper Bold, Samik, Traditional, Traditional Bold
AsoSoft.AliWeb2Unicode("هةر جةرةيانصکي مصذووُيي کة أوو دةدا");
>ھەر جەرەیانێکی مێژوویی کە ڕوو دەدا<
Dylan2Unicode
converts Kurdish text written in Dylan fonts (developed by Dylan Saleh at KurdSoft in 2001) into Unicode standard.
AsoSoft.Dylan2Unicode("لثكؤلثنةران بؤيان دةركةوتووة كة دةتوانث بؤ لةش بةكةصك بث");
>لێکۆلێنەران بۆیان دەرکەوتووە کە دەتوانێ بۆ لەش بەکەڵک بێ<
Zarnegar2Unicode
converts Kurdish text written in Zarnegar word processor (developed by SinaSoft with RDF converter by NoorSoft) and into Unicode standard.
AsoSoft.Zarnegar2Unicode("بلٌيٌين و بگهرٍيٌين بوٌ ههلاٌلٌهى سىٌيهمى فهلسهفه");
>بڵێین و بگەڕێین بۆ هەڵاڵەی سێیەمی فەلسەفە<
NormalizePunctuations
corrects spaces before and after of the punctuations. When seprateAllPunctuations
is true,
AsoSoft.NormalizePunctuations("دەقی«کوردی » و ڕێنووس ،((خاڵبەندی )) چۆنە ؟", false);
>دەقی «کوردی» و ڕێنووس، «خاڵبەندی» چۆنە؟<
Trim starting and ending white spaces (including zero width spaces) of line,
TrimLine
AsoSoft.TrimLine(" دەق\u200c ");
>دەق<
ReplaceHtmlEntity
replaces HTML Entities with single Unicode characters (e.g. "é" with "é"). It is useful in web crawled corpora.
AsoSoft.ReplaceHtmlEntity("ئێوە "دەق" لە زمانی <کوردی> دەنووسن");
>ئێوە "دەق" بە زمانی <کوردی> دەنووسن<
ReplaceUrlEmail
replaces URLs and emails with a certain word. It improves language models.
UnifyNumerals
unifies numeral characters into desired numeral type from en
(0123456789) or ar
(٠١٢٣٤٥٦٧٨٩)
AsoSoft.UnifyNumerals("ژمارەکانی ٤٥٦ و ۴۵۶ و 456", "en");
>ژمارەکانی 456 و 456 و 456<
SeperateDigits
add a space between joined numerals and words (e.g. replacing "12کەس" with "12 کەس"). It improves language models.
AsoSoft.SeperateDigits("لە ساڵی1950دا1000دۆلاریان بە 5کەس دا");
>لە ساڵی 1950 دا 1000 دۆلاریان بە 5 کەس دا<
Word2WordReplacement
applies a "string to string" replacement dictionary on the text. It replaces the full-matched words not a part of them.
var dict = new Dictionary<string, string>() { { "مال", "ماڵ" } };
AsoSoft.Word2WordReplacement("مال، نووری مالیکی", dict);
>ماڵ، نووری مالیکی<
Char2CharReplacment
applies a "char to char" replacement dictionary on the text. It uses as the final step needed for some non-Unicode systems.
It converts numerals into Central Kurdish words. It is useful in text-to-speech tools.
- integers (1100 => )
- floats (10.11)
- negatives (-10.11)
- percent (100% or %100)
- querency marks ($100, £100, and €100)
AsoSoft.Number2Word("لە ساڵی 1999دا بڕی 40% لە پارەکەیان واتە $102.1 یان وەرگرت");
>لە ساڵی هەزار و نۆسەد و نەوەد و نۆدا بڕی چل لە سەد لە پارەکەیان واتە سەد و دوو پۆینت یەک دۆلاریان وەرگرت<
Sorting a string list in correct order of Kurdish alphabet ("ئءاآأإبپتثجچحخدڎذرڕزژسشصضطظعغفڤقكکگلڵمنوۆۊۉهھەیێ")
var myList = new List<string>{"یەک", "ڕەنگ", "ئەو", "ئاو", "ڤەژین", "فڵان"}
AsoSoft.KurdishSort(myList);
>"ئاو", "ئەو", "ڕەنگ", "فڵان", "ڤەژین", "یەک"<
or using your custom order:
AsoSoft.CustomSort(List<string> inputList, List<char> inputOrder);
It classifies the meter of the input Kurdish poem typed in Arabic script. The lines of the poem should be seprated by new line char ('\n'). You can find Kurdish poems in https://books.vejin.net/.
var poem = AsoSoft.PoemNormalization(@"گەرچی تووشی ڕەنجەڕۆیی و حەسرەت و دەردم ئەمن
قەت لەدەس ئەم چەرخە سپڵە نابەزم مەردم ئەمن
ئاشقی چاوی کەژاڵ و گەردنی پڕ خاڵ نیم
ئاشقی کێو و تەلان و بەندەن و بەردم ئەمن");
var syllabified = AsoSoft.G2P(poem, true, true, true).Split('\n');
var classified = AsoSoft.PoemClassification(syllabified);
var poemType = classified.overalMeterType;
var poemMeter = classified.overalPattern;
Install AsoSoft Library package via NuGet Gallery.
Then, insert using AsoSoftLibrary;
into "Usings" of your codes.
AsoSoft Library is developed and maintained by Aso Mahmudi. AsoSoft Library is written in C# (.NET 6).