Skip to content

List of Todo #1

Description

@nileshprasad137
  • Properly handle Named Entity Recognition
  • Handle Punctuations
  • Look for suitable Machine Algo to train -PCA, SVM, Artificial Neural Networks, Multiple Linear Regression
  • Split into training and test set and train on all 8 sets of essays and calculate accuracy. Plot graphs. (Kappa Values)
  • Improve Spelling Accuracy
  • Add more features in dataframe
    - No. of Stop Words in Sentence
    - Average length of Sentence in an essay
  • Improve code modularity (if possible, least preference)
  • Normalize wrong spellings, word count (on Scale of 1-100)
  • Optimize code (Time Complexity and Space complexity)
  • If time permits, Use Word2Vec, TextRank to understand sentence Structure. ( Less preference)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions