Search Results for author:
Found 2 papers, 0 papers with code
Topic-DPR: Topic-based Prompts for Dense Passage Retrieval
Prompt-based learning's efficacy across numerous natural language processing tasks has led to its integration into dense passage retrieval.
Identical and Fraternal Twins: Fine-Grained Semantic Contrastive Learning of Sentence Representations
While the InfoNCE loss function overlooks the semantic margin and prioritizes similarity maximization between positive pairs during training, leading to the insensitive semantic comprehension ability of the trained model.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
