Machine Learning Final Project

Kaggle Competition: Jigsaw Unintended Bias in Toxicity Classification

TODO

一些优化方向思路，仅供参考:D

• EDA

• Preprocess

  可参考之前比赛的思路，解决OOV问题

  • BPE
  • TTA

• Model

  • Sequence model: bilstm, HAN...
  • Bert fine tune

• Metrics

  • 实现比赛AUC指标评测方法

• Argument

  • Adversarial Training

• Tricks

  • multi-task
  • sample_weights

Preprocessed Data

• Managed with git-lfs (X): can not upload new objects to public fork
• Dealing with OOV and data imbalanced problem