Joint Language Semantic and Structure Embedding for Knowledge Graph Completion
This work addresses knowledge graph completion for applications requiring accurate triplet predictions, offering a novel integration of semantics and structure that enhances performance, especially with limited data.
The paper tackles knowledge graph completion by jointly embedding semantic information from natural language descriptions with structural information, achieving state-of-the-art performance on various benchmarks and showing significant improvements in low-resource settings.
The task of completing knowledge triplets has broad downstream applications. Both structural and semantic information plays an important role in knowledge graph completion. Unlike previous approaches that rely on either the structures or semantics of the knowledge graphs, we propose to jointly embed the semantics in the natural language description of the knowledge triplets with their structure information. Our method embeds knowledge graphs for the completion task via fine-tuning pre-trained language models with respect to a probabilistic structured loss, where the forward pass of the language models captures semantics and the loss reconstructs structures. Our extensive experiments on a variety of knowledge graph benchmarks have demonstrated the state-of-the-art performance of our method. We also show that our method can significantly improve the performance in a low-resource regime, thanks to the better use of semantics. The code and datasets are available at https://github.com/pkusjh/LASS.