Papers by Qingfa Xiao

1 papers
Topic-DPR: Topic-based Prompts for Dense Passage Retrieval (2023.findings-emnlp)

Copied to clipboard

Challenge: Prior research focused on optimizing a single prompt as a continuous prompt, but this approach leads to a semantic space collapse, preventing differentiation between relevant and irrelevant passages.
Approach: They propose a dense passage retrieval model that uses topic-based prompts and propose 'positive and negative sampling strategies' to boost dense retrieval efficiency.
Outcome: The proposed model surpasses state-of-the-art retrieval techniques and improves space uniformity.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations