Knowledge Graph Refinement based on Triplet BERT-Networks
This work addresses knowledge graph refinement for tasks like graph completion and triple classification, offering incremental improvements in performance.
The paper tackled knowledge graph refinement by proposing GilBERT, a transformer-based triplet network that creates embeddings from textual sequences, achieving better or comparable results to state-of-the-art on tasks like triplet classification and relation prediction across benchmarks such as FB13, WN11, and FB15K.
Knowledge graph embedding techniques are widely used for knowledge graph refinement tasks such as graph completion and triple classification. These techniques aim at embedding the entities and relations of a Knowledge Graph (KG) in a low dimensional continuous feature space. This paper adopts a transformer-based triplet network creating an embedding space that clusters the information about an entity or relation in the KG. It creates textual sequences from facts and fine-tunes a triplet network of pre-trained transformer-based language models. It adheres to an evaluation paradigm that relies on an efficient spatial semantic search technique. We show that this evaluation protocol is more adapted to a few-shot setting for the relation prediction task. Our proposed GilBERT method is evaluated on triplet classification and relation prediction tasks on multiple well-known benchmark knowledge graphs such as FB13, WN11, and FB15K. We show that GilBERT achieves better or comparable results to the state-of-the-art performance on these two refinement tasks.