ADAPTED RERANK MODEL

GenGO

Omakase Read Later

Search

Papers with adapted rerank model

Findings

2023.findings-emnlp

dense retrieval models
unadapted rerank models
rerank model
adaptation process
dense retrieval model
adapted retrieval model
adapted rerank model
domain adaptation
pseudo queries
label generation

2023

Low-Resource NLP

1 papers

Breaking Boundaries in Retrieval Systems: Unsupervised Domain Adaptation with Denoise-Finetuning (2023.findings-emnlp)

Copied to clipboard

Che Chen, Ching Yang, Chun-Yi Lin, Hung-Yu Kao

Low-Resource NLP

Challenge:	Existing domain adaptation methods for dense retrieval models use unadapted rerank models, leading to imprecise labels.
Approach:	They propose to adapt a rerank model to the target domain before using it for label generation.
Outcome:	The proposed model achieves better results across three retrieval datasets.

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