Skip to content

Improving Knowledge Graph Embedding Using Simple Constraints (ACL-2108)

Notifications You must be signed in to change notification settings

iieir-km/ComplEx-NNE_AER

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 

Repository files navigation

ComplEx-NNE+AER

Codes and datasets for "Improving Knowledge Graph Embedding Using Simple Constraints" (ACL-2018)

Introduction

The repository provides java implementations and DB100K dataset used for the paper:

As well as the implementations for the following papers:

Datasets

Files

Datasets we used are in the corresponding subfolder contained in datasets/ with the following formats:

  • _train.txt,_valid.txt,_test.txt; training, valid, test set with string id; format: e1\tr\te2\n
  • _cons.txt; approximate entailment constraints; formant: r1,r2\tconfidence\n, where '-' denotes the inversion

Preprocessing

python data.py data_folder

Codes

Run the code

java -jar -train data_folder/train.txt -valid data_folder/valid.txt -test data_folder/test.txt

Parameters

You can changes parameter when training the model

k = number of dimensions
lmbda = L2 regularization coffecient
neg = number of negative samples
mu = AER regularization coffecient

Citation

@inproceedings{boyang2018:aer,
	author = {Ding, Boyang and Wang, Quan and Wang, Bin and Guo, Li},
	booktitle = {56th Annual Meeting of the Association for Computational Linguistics},
	title = {Improving Knowledge Graph Embedding Using Simple Constraints},
	year = {2018}
}

Contact

For all remarks or questions please contact Quan Wang: wangquan (at) iie (dot) ac (dot) cn .

About

Improving Knowledge Graph Embedding Using Simple Constraints (ACL-2108)

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published