Skip to content

GitLab

  • Menu
Projects Groups Snippets
    • Loading...
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
  • Sign in / Register
  • F FEDOT
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 87
    • Issues 87
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 1
    • Merge requests 1
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Monitor
    • Monitor
    • Incidents
  • Packages & Registries
    • Packages & Registries
    • Package Registry
    • Container Registry
    • Infrastructure Registry
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • ITMO-NSS-team
  • FEDOT
  • Issues
  • #198

Closed
Open
Created Dec 03, 2020 by Elizaveta Lutsenko@LizLutsenkoOwner

[InputData] Support texts as InputData

Created by: J3FALL

Impement experimental pipeline with simple NLP-model (or even NaiveBayesClassifier) for text classification/sentiment analysis:

  • New InputData format with generator-based logic (for texts batch-loading)
  • New simple model (for instance, CNN) or adoptation the existing models that are suitable for text classification
  • Maybe bag-of-words, word-2-vec model, etc. for text embeddings
  • Several text preprocessing methods (stemming, lemmatization, filtering, etc.)
  • Example of dataset where pipeline can be applied (spam classification for instance as the simpliest case)
  • Example of FEDOT pipeline that can solve the given task
Assignee
Assign to
Time tracking