yao8839836 / Kg Bert
Licence: apache-2.0
KG-BERT: BERT for Knowledge Graph Completion
Stars: ✭ 254
Programming Languages
python
139335 projects - #7 most used programming language
Labels
Projects that are alternatives of or similar to Kg Bert
PheKnowLator
PheKnowLator: Heterogeneous Biomedical Knowledge Graphs and Benchmarks Constructed Under Alternative Semantic Models
Stars: ✭ 74 (-70.87%)
Mutual labels: knowledge-graph
Interstellar
Interstellar: Searching Recurrent Architecture for Knowledge Graph Embedding. NeurIPS 2020.
Stars: ✭ 28 (-88.98%)
Mutual labels: knowledge-graph
HyperKA
Knowledge Association with Hyperbolic Knowledge Graph Embeddings, EMNLP 2020
Stars: ✭ 27 (-89.37%)
Mutual labels: knowledge-graph
KNET
Neural Entity Typing with Knowledge Attention
Stars: ✭ 65 (-74.41%)
Mutual labels: knowledge-graph
PathCon
Combining relational context and relational paths for knowledge graph completion
Stars: ✭ 29 (-88.58%)
Mutual labels: knowledge-graph
bangle-io
A web only WYSIWYG note taking app that saves notes locally in markdown format.
Stars: ✭ 626 (+146.46%)
Mutual labels: knowledge-graph
Kgcn
A tensorflow implementation of Knowledge Graph Convolutional Networks
Stars: ✭ 255 (+0.39%)
Mutual labels: knowledge-graph
LME
Neural Entity Typing with Language Model Enhancement
Stars: ✭ 21 (-91.73%)
Mutual labels: knowledge-graph
NMN
Source code and datasets for ACL 2020 paper: Neighborhood Matching Network for Entity Alignment.
Stars: ✭ 55 (-78.35%)
Mutual labels: knowledge-graph
covid-19-community
Community effort to build a Neo4j Knowledge Graph (KG) that links heterogeneous data about COVID-19
Stars: ✭ 95 (-62.6%)
Mutual labels: knowledge-graph
LinkedDataHub
The Knowledge Graph notebook. Apache license.
Stars: ✭ 150 (-40.94%)
Mutual labels: knowledge-graph
ke-dialogue
KE-Dialogue: Injecting knowledge graph into a fully end-to-end dialogue system.
Stars: ✭ 39 (-84.65%)
Mutual labels: knowledge-graph
TransE-Knowledge-Graph-Embedding
TensorFlow implementation of TransE and its extended models for Knowledge Representation Learning
Stars: ✭ 64 (-74.8%)
Mutual labels: knowledge-graph
PathCon
Combining relational context and relational paths for knowledge graph completion
Stars: ✭ 94 (-62.99%)
Mutual labels: knowledge-graph
sage
An Open Source Knowledge Graph written in Rust
Stars: ✭ 12 (-95.28%)
Mutual labels: knowledge-graph
Kenlg Reading
Reading list for knowledge-enhanced text generation, with a survey
Stars: ✭ 257 (+1.18%)
Mutual labels: knowledge-graph
typedb-loader
TypeDB Loader - Data Migration Tool for TypeDB
Stars: ✭ 43 (-83.07%)
Mutual labels: knowledge-graph
DeepEE
DeepEE: Deep Event Extraction Algorithm Gallery (基于深度学习的开源中文事件抽取算法汇总)
Stars: ✭ 24 (-90.55%)
Mutual labels: knowledge-graph
KG-BERT: BERT for Knowledge Graph Completion
The repository is modified from pytorch-pretrained-BERT and tested on Python 3.5+.
Installing requirement packages
pip install -r requirements.txt
Data
(1) The benchmark knowledge graph datasets are in ./data.
(2) entity2text.txt or entity2textlong.txt in each dataset contains entity textual sequences.
(3) relation2text.txt in each dataset contains relation textual sequences.
Reproducing results
1. Triple Classification
WN11
python run_bert_triple_classifier.py
--task_name kg
--do_train
--do_eval
--do_predict
--data_dir ./data/WN11
--bert_model bert-base-uncased
--max_seq_length 20
--train_batch_size 32
--learning_rate 5e-5
--num_train_epochs 3.0
--output_dir ./output_WN11/
--gradient_accumulation_steps 1
--eval_batch_size 512
FB13
python run_bert_triple_classifier.py
--task_name kg
--do_train
--do_eval
--do_predict
--data_dir ./data/FB13
--bert_model bert-base-cased
--max_seq_length 200
--train_batch_size 32
--learning_rate 5e-5
--num_train_epochs 3.0
--output_dir ./output_FB13/
--gradient_accumulation_steps 1
--eval_batch_size 512
2. Relation Prediction
FB15K
python3 run_bert_relation_prediction.py
--task_name kg
--do_train
--do_eval
--do_predict
--data_dir ./data/FB15K
--bert_model bert-base-cased
--max_seq_length 25
--train_batch_size 32
--learning_rate 5e-5
--num_train_epochs 20.0
--output_dir ./output_FB15K/
--gradient_accumulation_steps 1
--eval_batch_size 512
3. Link Prediction
WN18RR
python3 run_bert_link_prediction.py
--task_name kg
--do_train
--do_eval
--do_predict
--data_dir ./data/WN18RR
--bert_model bert-base-cased
--max_seq_length 50
--train_batch_size 32
--learning_rate 5e-5
--num_train_epochs 5.0
--output_dir ./output_WN18RR/
--gradient_accumulation_steps 1
--eval_batch_size 5000
UMLS
python3 run_bert_link_prediction.py
--task_name kg
--do_train
--do_eval
--do_predict
--data_dir ./data/umls
--bert_model bert-base-uncased
--max_seq_length 15
--train_batch_size 32
--learning_rate 5e-5
--num_train_epochs 5.0
--output_dir ./output_umls/
--gradient_accumulation_steps 1
--eval_batch_size 135
FB15k-237
python3 run_bert_link_prediction.py
--task_name kg
--do_train
--do_eval
--do_predict
--data_dir ./data/FB15k-237
--bert_model bert-base-cased
--max_seq_length 150
--train_batch_size 32
--learning_rate 5e-5
--num_train_epochs 5.0
--output_dir ./output_FB15k-237/
--gradient_accumulation_steps 1
--eval_batch_size 1500
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].