Although deep pre-trained language models have shown promising benefit i...
Deploying pre-trained transformer models like BERT on downstream tasks i...
Embedding models have shown great power in knowledge graph completion (K...
Recent studies have shown that dual encoder models trained with the
sent...
ELECTRA, the generator-discriminator pre-training framework, has achieve...
While generative modeling has been ubiquitous in natural language proces...
Current state-of-the-art document retrieval solutions mainly follow an
i...
The effectiveness of knowledge graph embedding (KGE) largely depends on ...