CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge

Jin, Zhuoran; Men, Tianyi; Yuan, Hongbang; He, Zhiyuan; Sui, Dianbo; Wang, Chenhao; Zhang, Xue; Chen, Yubo; Zhao, Jun

doi:10.18653/v1/2022.acl-demo.16

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous embedding-based KGE methods, such as TransE (Bordes et al, 2013), involved embedding relational knowledge into a vector space and subsequently optimizing the target object by applying a pre-defined scoring function to those vectors. A few remarkable embedding-based KGE toolkits have been developed, such as OpenKE (Han et al, 2018), LibKGE (Broscheit et al, 2020), PyKEEN (Ali et al, 2021), CogKGE (Jin et al, 2022) and NeuralKG (Zhang et al, 2022c). Nevertheless, these embedding-based KGE approaches are restricted in expressiveness regarding the shallow network architectures without using any side information (e.g., textual description).…”

Section: Introductionmentioning

confidence: 99%

LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings

Xie,

Li,

Wang

et al. 2023

Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacifi

View full text Add to dashboard Cite

Knowledge Graphs (KGs) often have two characteristics: heterogeneous graph structure and text-rich entity/relation information. Textbased KG embeddings can represent entities by encoding descriptions with pre-trained language models, but no open-sourced library is specifically designed for KGs with PLMs at present. In this paper, we present LambdaKG, a library for KGE that equips with many pretrained language models (e.g., BERT, BART, T5, GPT-3) and supports various tasks (e.g., knowledge graph completion, question answering, recommendation, and knowledge probing).LambdaKG is publicly open-sourced 1 , with a demo video 2 and long-term maintenance.

show abstract

Section: Introductionmentioning

confidence: 99%

LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings

Xie,

Li,

Wang

et al. 2023

Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacifi

View full text Add to dashboard Cite

show abstract

“…Previous embedding-based knowledge graph representation methods, such as TransE [2], embed the relational knowledge into a vector space and then optimize the target object by leveraging a pre-defined scoring function to those vectors. A few remarkable open-sourced and long-term maintained KG representation toolkits have been developed, such as OpenKE [5], LibKGE [3], PyKEEN [1], CogKGE [6]. Nevertheless, these embedding-based methods are restricted in expressiveness regarding the shallow network architectures without using any side information.…”

Section: Introductionmentioning

confidence: 99%

PromptKG: A Prompt Learning Framework for Knowledge Graph Representation Learning and Application

Xie¹,

Li²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Knowledge Graphs (KGs) often have two characteristics: heterogeneous graph structure and text-rich entity/relation information. KG representation models should consider graph structures and text semantics, but no comprehensive open-sourced framework is mainly designed for KG regarding informative text description. In this paper, we present PromptKG, a prompt learning framework for KG representation learning and application that equips the cutting-edge text-based methods, integrates a new prompt learning model and supports various tasks (e.g., knowledge graph completion, question answering, recommendation, and knowledge probing). PromptKG is publicly open-sourced at https://github.com/zjunlp/PromptKG with long-term technical support.

show abstract

CogKGE: A Knowledge Graph Embedding Toolkit and Benchmark for Representing Multi-source and Heterogeneous Knowledge

Cited by 2 publications

References 0 publications

LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings

LambdaKG: A Library for Pre-trained Language Model-Based Knowledge Graph Embeddings

PromptKG: A Prompt Learning Framework for Knowledge Graph Representation Learning and Application

Contact Info

Product

Resources

About