oooo26 / CS4248_project

4-way document classification on Labeled Unreliable News (LUN) dataset.

CS4248 Project

4-way document classification on Labeled Unreliable News (LUN) dataset. All preprocessing (including feature extraction) and models can be checked in models\*.

• Intermediate Update: [link]
• Final Report: [link]
• Final Report Template: https://www.overleaf.com/read/spjdcnpvcgyk
• Canvas Q&A: https://canvas.nus.edu.sg/courses/38713/discussion_topics/49999

Time Schedule

• First Meeting (February 12th)
• Second Meeting (February 28th)
• Intermediate (March 2rd)
• Preprocessing (March 19th)
  • Zhehao - Data Preprocessing, data augmentation, etc
• Model implementation (March 31st)
  • Trushti - tf-idf based naive bayes and logistic regression
  • Zhehao - Transformer & Performer
  • Rongrong - BiLSTM & small BERT
  • Junhao - RoBERTa
  • Sagar - XLNet
• Report (April 6th)

Team Member

• Zhehao Gu
• Rongrong Zhan
• Sagar Sureka
• Modi Trushti Sanjaybhai
• Junhao Huang