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

TL;DR

LambdaKG is an open-source library that leverages pre-trained language models for knowledge graph embeddings, supporting multiple tasks and providing a unified framework for text-rich KGs.

Contribution

It introduces a comprehensive library integrating various PLMs for KGE, tailored for heterogeneous, text-rich knowledge graphs, filling a gap in existing tools.

Findings

Supports multiple pre-trained language models like BERT, BART, T5, GPT-3.

Enables various tasks including KG completion, question answering, and recommendation.

Open-sourced with ongoing maintenance and a demo available.

Abstract

Knowledge Graphs (KGs) often have two characteristics: heterogeneous graph structure and text-rich entity/relation information. Text-based 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 pre-trained 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 at https://github.com/zjunlp/PromptKG/tree/main/lambdaKG, with a demo video at http://deepke.zjukg.cn/lambdakg.mp4 and long-term maintenance.