Skip to content

Source code and datasets of paper: Complex Question Answering over Knowledge Base with Multi-Attention RNN.

Notifications You must be signed in to change notification settings

wds-seu/KBQA-multi-attention-RNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

KBQA-multi-attention-RNN

Source code and datasets of paper: A Multi-Attention RNN Based Relation Linking Approach for Ques-tion Answering over Knowledge Base.

Requirements

jieba 0.39
python 3.6
keras 2.2.4
nltk 3.4.5
numpy 1.16.5
scikit-learn 0.21.2
tensorflow 1.14.0
tqdm 4.32.1

Datasets

LC_Quad

Run and Test

  • entity_linking
python build_data.py      
python train.py  
python evaluate.py
  • relation_detection
python preprocess.py
python model_twoatt_con.py
python eval_twoatt_con.py

About

Source code and datasets of paper: Complex Question Answering over Knowledge Base with Multi-Attention RNN.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published