Difference between revisions of "Central Kurdish"
From LING073
(→Computational Resources) |
|||
Line 11: | Line 11: | ||
* Latin-based keyboard layout that I own on my computer | * Latin-based keyboard layout that I own on my computer | ||
− | * [https://arxiv.org/abs/1911.13087 Kurdish Speech to Text]: attempt to develop speech recognition for Sorani Kurdish | + | * [https://arxiv.org/abs/1911.13087 Kurdish Speech to Text]: early attempt to develop speech recognition for Sorani Kurdish |
+ | |||
+ | * [https://arxiv.org/abs/2010.06041 Towards Machine Translation for the Kurdish Language]: attempt to develop machine translation for Sorani | ||
== Dictionaries == | == Dictionaries == |
Revision as of 22:42, 18 February 2021
Below is a list of resources relevant to the Sorani Kurdish language. Resources are categorized according to type of content. I own italicized resources in PDF format. I have also flagged resources I have not yet obtained.
Contents
Computational Resources
- .txt lists of words, word-level digrams, and character-level trigrams
- Keyboard Layout: seems to be the most common layout
- Latin-based keyboard layout that I own on my computer
- Kurdish Speech to Text: early attempt to develop speech recognition for Sorani Kurdish
- Towards Machine Translation for the Kurdish Language: attempt to develop machine translation for Sorani
Dictionaries
- Sorani Vocabulary: vocab list with Latin script transliterations, by Harvard
- The Kurdish Dictionary: translates to and from any combination of ckb/kur/eng via query
- Diccionaire Fondamental Kurde-Français-Sorani: French-Sorani dict with phrases & alphabet
Grammatical Descriptions
- Kurdish Basic Course: has helpful chapters on grammar and word lists
- Sorani Grammar: extensive descriptions of Sorani grammar
Scientific Works
- Building a Lemmatizer and a Spell-Checker for Sorani Kurdish: includes background on Sorani morphology
- Kurdish Romanization Table: potentially useful information on Sorani alphabet and orthography
- Kurdish Interdialect Machine Translation: suggests a method for Kurmanji-Sorani machine translation
Corpora
Books & Encyclopediae
- Sorani Wikipedia: many articles averaging a few paragraphs in length
- Sorani Bible: one of a few different versions of the Bible
- JW Website: few dozen entries accompanied by voice narration
- Hawler Gov: various entries on the Kurdish capital
- شازاده چکۆله: Sorani version of The Little Prince, by Aso Abdullah
News Sites
This is an aggregation of news sites, all written in Sorani, that contain written media on the order of ~300 words per article, though long-form works of journalism can also be found.
Blog Pages
Long-form posts that exceed ~1000 words can be found here. Each link goes to a specific person's blog archive, containing anywhere between 10-100 articles.
- Abas Shiwan (with Latin script transliterations)