https://github.com/saidziani/sumrized

Automatic Text Summarization (English/Arabic).
https://github.com/saidziani/sumrized

arabic-nlp nlp-machine-learning text-summarization

Last synced: over 1 year ago
JSON representation

Automatic Text Summarization (English/Arabic).

• Host: GitHub
• URL: https://github.com/saidziani/sumrized
• Owner: saidziani
• License: gpl-3.0
• Created: 2017-12-05T22:50:35.000Z (over 8 years ago)
• Default Branch: master
• Last Pushed: 2018-07-01T11:05:46.000Z (about 8 years ago)
• Last Synced: 2024-04-23T01:55:25.539Z (about 2 years ago)
• Topics: arabic-nlp, nlp-machine-learning, text-summarization
• Language: Jupyter Notebook
• Homepage: http://sumrized.com/
• Size: 9.74 MB
• Stars: 37
• Watchers: 4
• Forks: 9
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

          


    

        

    



# Arabic Text Summarization

## Starting Project

* Make sure you have installed pip (Python 3)

    ```text

    sudo apt-get install python3-pip

    ```

* Make sure you have NLTK (Natural Language Tool Kit) installed  (Python 3)

    ```text

    sudo pip install -U nltk

    ```

## Project content 

```text

.  

├── docs                    <- All documentation about project

│   ├── reports             <- Reports for current project advancement 

│   ├── references          <- All references papers, links related to this project goes here   

│   └── sphinx              <- Automaticaly genereated API documentation form stringdocs in code

│

├── lib                     <- All project's source code goes here

│   ├── data-generation     <- Code for data generation if needed 

│   └── preprocessing       <- Code for data preprocessing 

│ 

├── models                  <- Contains code to train, test and run models 

│   ├── dumps               <- trained models file

│   └── scripts             <- script to run models 

│ 

├── Readme.md               <- Contains current project info

├── requirements.txt        <- Packages and modules needed for the current project to run

└── tests                   <- Unit test for the code in lib/ 

    └── lib  

        ├── analysis  

        ├── data-generation   

        └── preprocessing

   

```

  

## Guide lines

### Data

* Symlink to your Raw data

    ```text

        user@host:/my/awesome/project$ ln -s /path/to/your/raw/data . 

    ```

* Data location must follow this structure:

```

data  

├── raw             <- Raw data

├── temp            <- transformed data stored temporarily if needed 

└── preprocessed    <- preprocessed data to run in a model

```

#### Data is immutable  

* Treat the data/raw (and its format) as immutable. Don't ever edit your raw data, especially not manually, and 

especially not in Excel.

* Don't overwrite your raw data. Don't save multiple versions of the raw data.

* The code you write should move the raw data through a pipeline to your final analysis.

* You shouldn't have to run all of the steps every time you want to make a new figure, 

but anyone should be able to reproduce the final products with only the code in lib/ and the data in data/raw.