Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track

Guangwei Xu, Yangzhao Zhang, Longhui Zhang, Dingkun Long, Pengjun Xie +1 more
8/23/2023
cs.IRcs.CL

No confident code implementation found for this paper.

Abstract

Large-scale text retrieval technology has been widely used in various practical business scenarios. This paper presents our systems for the TREC 2022 Deep Learning Track. We explain the hybrid text retrieval and multi-stage text ranking method adopted in our solution. The retrieval stage combined the two structures of traditional sparse retrieval and neural dense retrieval. In the ranking stage, in addition to the full interaction-based ranking model built on large pre-trained language model, we also proposes a lightweight sub-ranking module to further enhance the final text ranking performance. Evaluation results demonstrate the effectiveness of our proposed approach. Our models achieve the 1st and 4th rank on the test set of passage ranking and document ranking respectively.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering

85% match2022

Zero-Shot Listwise Document Reranking with a Large Language Model

81% match2023

A Comparative Evaluation of Embeddings and LLMs in a Greek Book Publisher Setting - The CUP Dataset

81% match2026

Improving Neural Ranking Models with Traditional IR Methods

81% match2023

From BM25 to Corrective RAG: Benchmarking Retrieval Strategies for Text-and-Table Documents

81% match2026

UNIMIB at TREC 2021 Clinical Trials Track

80% match2022

Cite this paper

@article{xu2023hybrid,
  title  = {Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track},
  author = {Guangwei Xu and Yangzhao Zhang and Longhui Zhang and Dingkun Long and Pengjun Xie and Ruijie Guo},
  year   = {2023},
  eprint = {2308.12039},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.12039v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.12039.svg)](https://codeofpaper.com/paper/2308.12039)

Discussion