This package includes 3th solution for the "Yun Cup" Scenic Reputation Evaluation Score Forecast.
model: machine learning model & deel learning model meta feature for stacking purpose.preprocess: preprocesss for machine learning model.stacking: stacking model.yuntext: deep learning model(including detailed instructions to setup).
- Stacking get better performence in LB.
| model | score |
|---|---|
| FastText | 0.54018 (pretrained embedding) |
| Ridge | 0.54449 |
| Select-K-Best | ~0.543 |
| Word2vec | 0.549 |
| CNN | 0.556 |
| RCNN | 0.555 |
| Capsule | 0.549 |
| HAN(LSTM-Attention) | 0.550 |
| RNN | 0.547 |
- Data Augment
- TF-IDF-CD
- Crawl comments from scenic reputation website to pretrain word embeddings.
- Pseudo-Labelling
- Kaggle Toxic Comment Classification Challenge
- Large Scale Multi-label Text Classification With Deep Learning
- Convolutional Neural Networks for Sentence Classification
- Recurrent Convolutional Neural Networks for Text Classification
- Neural Machine Translation of Rare Words with Subword Units
- A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification