← Search

Anlei Dong

2 accepted papers

2023

CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion

EMNLP 2023long main

The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and document. To alleviate this, recent research has focused on obta…

Cited by 0SourcecodeScholar
2022

SimANS: Simple Ambiguous Negatives Sampling for Dense Text Retrieval

EMNLP 2022industry

Sampling proper negatives from a large document pool is vital to effectively train a dense retrieval model. However, existing negative sampling strategies suffer from the uninformative or false negative problem. In this work, we empirically show that according to the measured relevance scores, the n…