QACNN : Query-based Attention CNN

Implementation of the research: Query-based Attention CNN for Text Similarity Map (https://arxiv.org/abs/1709.05036

)

all files in 6 folders and 1 main script should be included

• preprocess
  • plot2vec.py
  • qa2vec.py
• word_vec
  • register.json
  • glove.42B.300d.json
• raw_data
  • plot
    • IMDB_KEY.split.wiki
  • question
    • qa.json
• output_data
  • plot
  • question
• utility
  • utility.py
• model
  • MODEL.py
• main.py

Usage

1. Input data given by MovieQA into raw_data folder (including IMDB_KEY.split.wiki and qa.json). qa.json 在此 gitlab repo 下載 https://github.com/makarandtapaswi/MovieQA_benchmark/tree/master/data；IMDB_KEY.split.wiki 在 ...

2. Download GloVe word2vec and put it into word_vec folder (GloVe:
   https://drive.google.com/file/d/0B3UsyrHYzsTzekMtbndMZXB1Ync/view?usp=sharing)

3. Run 2 scripts (plot2vec.py & qa2vec.py), and the preprocessed data will automatically be saved to output_data folder

4. Run main.py

Reference

[0]

https://github.com/chun5212021202/QACNN