CokeBERT utilizes a Large Language Model to encode word tokens and extracts knowledge contexts from Knowledge Graphs for each entity detected in text, with word and knowledge embeddings fused using the K-Encoder.

Authors

• Person: Not available Organization: arXiv
  Combining Knowledge Graphs and Large Language Models - arXiv

Sources

• Combining Knowledge Graphs and Large Language Models - arXiv arxiv.org arXiv via serper

Referenced by nodes (1)

• knowledge graphs concept