OpenKE: An Open Toolkit for Knowledge Embedding

By Xu Han, Shulin Cao, Xin Lv, Yankai Lin, Zhiyuan Liu, Maosong Sun, Juan-Zi Li. 2018

371 citations recorded by the source corpus.

We release an open toolkit for knowledge embedding (OpenKE), which provides a unified framework and various fundamental models to embed knowledge graphs into a continuous low-dimensional space. OpenKE prioritizes operational efficiency to support quick model validation and large-scale knowledge representation learning. Meanwhile, OpenKE maintains sufficient modularity and extensibility to easily incorporate new models into the framework. Besides the toolkit, the embeddings of some existing large-scale knowledge graphs pre-trained by OpenKE are also available, which can be directly applied for many applications including information retrieval, personalized recommendation and question answering. The toolkit, documentation, and pre-trained embeddings are all released on http://openke.thunlp.org/.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Wei Hu
2. Zequn Sun
3. Graham Neubig
4. Hao Peng
5. Liang Yao
6. Chengsheng Mao
7. Chenyan Xiong
8. Muhao Chen

Citations in the corpus

• Latent Relation Language Models (2019, methodology): “We utilize pre-trained KG embeddings from OpenKE (Han et al. 2018) for entities and relation types.”
• A benchmarking study of embedding-based entity alignment for knowledge graphs (2020, positive): “TransH, TransR, TransD and HolE are developed by referring to the open-source toolkit OpenKE [27]; the remaining is implemented based on their source code.”
• KG-BERT: BERT for Knowledge Graph Completion (2019, methodology): “We test some classical baseline models with OpenKE toolkit (Han et al. 2018) 1 , other results are taken from the original papers.”
• A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, methodology): “Beyond the integrated deep learning toolkits, OpenKE and OpenEA, OpenNE 9 integrates embedding models such as Node2VEC [70] and LINE [71] to generate global representations from a complete knowledge graph.”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, neutral): “Notably, there are three useful toolkits, namely scikit-kge and OpenKE [206] for knowledge graph embedding, and OpenNRE [207] for relation extraction.”