Create a Text Classification Multilabel based project

Create a Text Classification Multilabel based project


Multilabel classification assigns different labels to a sample set. This process is similar to predicting properties of data-points that are not mutually exclusive. For example, a body of text about books could contain the authors name, publication location, title of the book, and publishing year. It could also contain none of these.  Skyl allows you to label these texts in multiple categories if necessary.

To create a Text Classification Multilabel  project:

  1. Select ‘Add Project’ on the Welcome page of Skyl.ai


  2. You will be directed to the ‘Select a Machine Learning Template for your Project’ page

  3. To create a text classification multilabel project, select ‘Text Classification Multilabel’ under ‘Natural language Processing’

  4. To learn more about Image Classification MultiLabel projects, select ‘Learn More’


  5. Choose “Select This template” to be directed to the ’Define your Project Name and Outcome’ page. From this page, enter a name and short description of your project

  6. Select ‘Create Project’ to create the project, or ‘Cancel’ to cancel the project

  7. For example: Twitter Sentiment Analysis


  8. Bio-Entity Recognition Task will appear on the Welcome Page of Skyl.




Create a Text Extraction Named-Entity Recognition based project

Create a Text Extraction Named-Entity Recognition based project


Named-Entity Recognition the process through which a computer processes unstructured text data and extracts key words under their respective labels.

For example, (Bio-Entity Recognition Task)

To create a Text Extraction Named-Entity Recognition project:

  1. Select ‘Add Project’ on the Welcome page of Skyl.ai


  2. You will be directed to the ‘Select a Machine Learning Template for your Project’ page

  3. Select ‘Text Extraction Named-Entity Recognition’ under ‘Natural language Processing’ to begin a Text Extraction Named-Entity Recognition project

  4. To learn more about Text Extraction Named-Entity Recognition projects, select ‘Learn More’ underneath the box


  5. Choose “Select This template” to be directed to the ’Define your Project Name and Outcome’ page. From this page, enter a name and short description of your project

  6. Select ‘Create Project’ to create the project, or ‘Cancel’ to cancel the project

  7. For example: Bio-Entity Recognition Task


  8. Bio-Entity Recognition Task will appear on the Welcome Page of Skyl.




Natural Language Processing Overview

Natural Language Processing Overview


Natural language processing (NLP) is the process through which computers read, understand, interpret, and respond to human language.  Any business that has a need to read and interpret text can adopt NLP. In Skyl, a user can create projects that classify text in both multiclass and multilabel cases. Users can extract and identify key words as well as summarize blocks of text using Skyl


Create a Text Classification Multiclass based project

Create a Text Classification Multiclass based project


Multiclassification is the process through which computers classify blocks of unstructured text that contain three or more categories underneath a single category. For example, a set of different new articles may be  about sports, politics, or entertainment. Multiclass classification assumes that each article can be assigned to a single label, so an article can be either a politics or a sports but not both at the same time.

To create a Text Classification Multiclass project:

  1. Select ‘Add Project’ on the Welcome page of Skyl.ai


  2. You will be directed to the ‘Select a Machine Learning Template for your Project’ page

  3. Select ‘Text Classification Multiclass’ under ‘Natural language Processing’ to begin a text classification multiclass project

  4. To learn more about Text Classification Multiclass projects, select ‘Learn More’ underneath the box


  5. Select “Select This Template” to be directed to the ’Define your Project Name and Outcome‘ page where you can enter a name and short description of your project

  6. Select ‘Create Project’ to create the project, or ‘Cancel’ to cancel the project

  7. For example: News Category Classification


  8. News Category Classification will appear on the Welcome Page of Skyl




Create an Image Classification Multilabel based project

Create an Image Classification Multilabel based project


Multilabel classification assigns different labels to a sample set. This process is similar to predicting properties of data-points that are not mutually exclusive.  For example: an image may contain buildings, trees, signs, the sky or people. It could also contain none of these. Skyl allows you to label these images in multiple categories if necessary.

To create an Image Classification Multilabel  project:

  1. Click the ‘Add Project’ card on the Welcome Page of Skyl.ai


  2. You will be directed to the page where you can select a Machine Learning template for your project
  3. To create an Image Classification Multilabel project, select the Image Classification Multilabel template under Computer Vision
  4. To learn more about the process of creating an image classification multilabel project, click ‘Learn more’


  5. By selecting the Image Classification Multilabel template, you will be directed to ’Define your Project Name and Outcome’. Here, enter the Name of the project and describe what Machine Learning outcome you want to achieve from the project

    For example: Vehicle Defect Detection for Insurance Claim


  6. When you create a project, you will be able to view it on the Skyl Welcome Page. When you select a particular project, you will be taken to the next stage; designing your dataset




Create an Image Classification Multiclass based project

Create an Image Classification Multiclass based project


MultiClass classification the process through which computers classify images that have three or more categories within a single label.

For example, a set of different fruits may be oranges, apples, or pears. Multiclass classification assumes that each fruit can be assigned to a single label: a fruit can be either an apple or a pear but not both at the same time.

To create an Image Classification Multiclass project:

  1. Select ‘Add Project’ on the Welcome page of Skyl.ai


  2. You will be directed to the page where you can select a Machine Learning template for your project
  3. To create an Image Classification Multiclass project, select the Image Classification Multiclass template under Computer Vision
  4. To learn more about the process of creating an image classification multiclass project, click ‘Learn more’

  5. By selecting the Image Classification Multiclass template, you will be directed to ’Define your Project Name and Outcome’. Here, enter the Name of the project and describe what Machine Learning outcome you want to achieve from the project

  6. Select ‘Create Project’ or ‘Cancel’ the project

  7. For example, your project name is ‘Pneumonia Detection’


  8. Once created, the project ‘Pneumonia Detection’ will appear on the Welcome Page






Computer Vision Overview

Computer Vision Overview


Computer vision in Skyl is the automatic extraction, analysis, and comprehension of useful information from an image or a sequence of images.  Skyl can create both image multiclass and multilabel projects.



Inviting a Project lead

Inviting a Project lead


A project lead can add or remove users from a project, activate or deactivate user accounts, and collaborate on a project.

  1. To invite a project lead, select the “Team Members” tab on the welcome page to your list of team members.

  2. From here, click “Invite Team Member” on the upper-right hand side of the page

  3. Once you invite a team member, fill in their name, email, and role

  4. Click “Invite Team Member” to invite the new project lead, or “Cancel” if you do not need a new team member



Selecting a Machine Learning Template

Selecting a Machine Learning Template


A machine learning template is a guided workflow that creates ML projects seamlessly. They simplify the ML process by allowing you to streamline your project depending upon your use-case.

You can choose between image classification, text classification, and natural language extraction templates. Respectfully, these templates help categorize images, classify text, and extract keywords from text.

ML templates customise options for data collection, data labelling, and even algorithms for machine learning depending on the use-case and suggestions.

  1. Select the "Add Project" box

  2. You will be directed to a templates page

  3. Choose between Computer Vision projects and Natural Language Processing projects

    1. Under Computer Vision, you can either choose Single Class or Multi Class image classification projects
    2. Under Natural Language Processing you can choose between Text Extraction, Text Classification, or Multi Label Classification projects
  4. After selecting your template, you will be able to name, describe, and add members to your project


Creating a Project

Creating a Project


A project in Skyl allows you to collect and label your data in a collaborative environment. When you create a project, the process of creating a streamlined machine learning project begins.  Skyl projects include text classification and computer vision projects.

In order to create a new project:

  1. Select the "Add Project" box


  2. Choose from the list of templates that appear on the following screen


  3. Enter a name and description for your project

Be sure to select the appropriate template to meet your project goals.