280
30
9
6
LambdaKG contains: 1) Core Module with Unified KG Encoder: LambdaKG utilizes a unified encoder to pack graph structure and text semantics, with convenient Trainer&Evaluator, Metric, and Bag of Tricks; 2) Model Hub: LambdaKG is integrated with many cutting-edge PLM-based KGE models; 3) Flexible Downstream Tasks: LambdaKG disentangles KG representation learning and downstream tasks.
LambdaKG consists of a Model Hub which supports many representative language model-based KGE models.
SimKGC adopts a biencoder discriminative architecture. Two encoders are initialized with the same pre-trained language model but do not share parameters.
A sequence-to-sequence generative model pre-trained from scratch - not initialized with the pre-trained LM weights, and optimized with head/tail prediction.
GPT-3 (Generative Pre-trained Transformer 3) is a natural language processing model developed by OpenAI that uses large-scale neural networks to generate natural language text.
kNN-KGE is a knowledge graph embedding approach with pre-trained language models by linearly interpolating its entity distribution with k-nearest neighbors.
KG-BERT treat triples in knowledge graphs as textual sequences and get the knowledge graph bidirectional encoder representations from Transformer to model these triples.
Structure-Augmented Text Representation (StAR) model for KGE which augment pre-trained language model with graph embedding techniques.
