/CapsE

A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization (NAACL 2019)

Primary LanguagePythonApache License 2.0Apache-2.0

A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search PersonalizationTwitter

GitHub top languageGitHub repo sizeGitHub last commitGitHub forksGitHub starsGitHub

This program provides the implementation of the capsule network-based model CapsE as described in the paper:

    @InProceedings{Nguyen2019CapsE,
      author={Dai Quoc Nguyen and Thanh Vu and Tu Dinh Nguyen and Dat Quoc Nguyen and Dinh Phung},
      title={A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization},
      booktitle={Proceedings of the 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)},
      year={2019},
      pages={2180--2189}
      }

Usage

Requirements

  • Python 3
  • Tensorflow >= 1.6

Training

    $ python CapsE.py --embedding_dim 100 --num_epochs 31 --num_filters 50 --learning_rate 0.0001 --name FB15k-237 --useConstantInit --savedEpochs 30 --model_name fb15k237
    
    $ python CapsE.py --embedding_dim 100 --num_epochs 31 --num_filters 400 --learning_rate 0.00001 --name WN18RR --savedEpochs 30 --model_name wn18rr

Evaluation metrics

Depending on the memory resources, you should change the values of --num_splits to a suitable value to get a faster process. To get the results (supposing num_splits = 8):

    $ python evalCapsE.py --embedding_dim 100 --num_filters 50 --name FB15k-237 --useConstantInit --model_index 30 --model_name fb15k237 --num_splits 8 --decode
    
    $ python evalCapsE.py --embedding_dim 100 --num_filters 400 --name WN18RR --model_index 30 --model_name wn18rr --num_splits 8 --decode

Note SEARCH17

As in an agreement, you have to cite the paper Search Personalization with Embeddings whenever SEARCH17 is used to produce your published results. Unzip doc2vec.200.zip in the data/SEARCH17 folder.

At the moment, I cannot release the text because of the privacy issues.

License

Please cite the paper whenever CapsE is used to produce published results or incorporated into other software. As a free open-source implementation, CapsE is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. All other warranties including, but not limited to, merchantability and fitness for purpose, whether express, implied, or arising by operation of law, course of dealing, or trade usage are hereby disclaimed. I believe that the programs compute what I claim they compute, but I do not guarantee this. The programs may be poorly and inconsistently documented and may contain undocumented components, features or modifications. I make no guarantee that these programs will be suitable for any application.

CapsE is is licensed under the Apache License 2.0.