https://github.com/linuxscout/miknaaz

Generate arabic golden standard corpus for morphology and stemming
https://github.com/linuxscout/miknaaz

Last synced: 3 months ago
JSON representation

Generate arabic golden standard corpus for morphology and stemming

• Host: GitHub
• URL: https://github.com/linuxscout/miknaaz
• Owner: linuxscout
• License: gpl-3.0
• Created: 2018-08-25T19:06:22.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2023-01-12T15:43:48.000Z (over 2 years ago)
• Last Synced: 2023-03-11T10:12:32.564Z (about 2 years ago)
• Language: Python
• Size: 86.9 KB
• Stars: 12
• Watchers: 2
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Miknaaz مكناز

## Description

Generate Arabic golden standard corpus for morphology and stemming 

### Citation

If you would cite it in academic work, can you use this citation

	Taha Zerrouki‏, Miknaaz,  http://github.com/linuxscout/miknaaz, 2023

or in bibtex format

	@misc{zerrouki2018miknaaz,

	  title={Miknaaz: Generate arabic golden standard},

	  author={Zerrouki, Taha},

	  url={http://github.com/linuxscout/miknaaz},

	  year={2018}

	}

## Usage

* Build word features for linguistics building corpus

```python

from miknaaz.corpus_builder import CorpusBuilder

text = u"إلى البيت"

lemmer = CorpusBuilder()

words = lemmer.tokenize(text)

for word in words:

    result = lemmer.morph_suggestions(word, True)

    print(result)

```

* Extract separate features

  ```python

  from miknaaz.corpus_builder import CorpusBuilder

  text = u"إلى البيت"

  lemmer = CorpusBuilder()

  words = lemmer.tokenize(text)

  # test get lemmas

  for word in words:

      result = lemmer.get_lemmas(word)

      # the result contains objects

      print(result)

  # test get roots

  for word in words:

      result = lemmer.get_roots(word)

      # the result contains objects

      print(result)

  # test get wordtypes

  for word in words:

      result = lemmer.get_word_type(word)

      # the result contains objects

      print(result)

  # test get wazns

  for word in words:

      result = lemmer.get_wazns(word)

      # the result contains objects

      print(result)

  ```