HyReC: Exploring Hybrid-based Retriever for Chinese

TL;DR

HyReC is a novel end-to-end method for hybrid Chinese retrieval that combines semantic union, a global-local-aware encoder, and normalization to improve performance and semantic consistency.

Contribution

It introduces HyReC, an innovative hybrid retrieval model with a GLAE and normalization modules, specifically designed for Chinese retrieval tasks.

Findings

HyReC outperforms existing methods on C-MTEB benchmark.

Semantic union enhances retrieval accuracy.

Glae and NM improve semantic sharing and alignment.

Abstract

Hybrid-based retrieval methods, which unify dense-vector and lexicon-based retrieval, have garnered considerable attention in the industry due to performance enhancement. However, despite their promising results, the application of these hybrid paradigms in Chinese retrieval contexts has remained largely underexplored. In this paper, we introduce HyReC, an innovative end-to-end optimization method tailored specifically for hybrid-based retrieval in Chinese. HyReC enhances performance by integrating the semantic union of terms into the representation model. Additionally, it features the Global-Local-Aware Encoder (GLAE) to promote consistent semantic sharing between lexicon-based and dense retrieval while minimizing the interference between them. To further refine alignment, we incorporate a Normalization Module (NM) that fosters mutual benefits between the retrieval approaches. Finally, we evaluate HyReC on the C-MTEB retrieval benchmark to demonstrate its effectiveness.