Contrastive Refinement for Dense Retrieval Inference in the Open-Domain Question Answering Task

Qiuhong Zhai, Wenhao Zhu, Xiaoyu Zhang and Chenyun Liu ()
Additional contact information
Qiuhong Zhai: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
Wenhao Zhu: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
Xiaoyu Zhang: School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China
Chenyun Liu: Shanghai Municipal Big Data Center, Shanghai 200444, China

Future Internet, 2023, vol. 15, issue 4, 1-14

Abstract: In recent years, dense retrieval has emerged as the primary method for open-domain question-answering (OpenQA). However, previous research often focused on the query side, neglecting the importance of the passage side. We believe that both the query and passage sides are equally important and should be considered for improved OpenQA performance. In this paper, we propose a contrastive pseudo-labeled data constructed around passages and queries separately. We employ an improved pseudo-relevance feedback (PRF) algorithm with a knowledge-filtering strategy to enrich the semantic information in dense representations. Additionally, we proposed an Auto Text Representation Optimization Model (AOpt) to iteratively update the dense representations. Experimental results demonstrate that our methods effectively optimize dense representations, making them more distinguishable in dense retrieval, thus improving the OpenQA system’s overall performance.

Keywords: dense retrieval; pseudo-reference feedback; pseudo-labels; semi-supervised learning (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2023
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/15/4/137/pdf (application/pdf)
https://www.mdpi.com/1999-5903/15/4/137/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:15:y:2023:i:4:p:137-:d:1113490

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().