Saved in:
Bibliographic Details
Main Authors: Qiao, Yixuan, Zhao, Shanshan, Wang, Jun, Chen, Hao, Liu, Tuozhen, Ye, Xianbin, Tang, Xin, Fang, Rui, Gao, Peng, Xie, Wenfeng, Xie, Guotong
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2205.11245
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915774499651584
author Qiao, Yixuan
Zhao, Shanshan
Wang, Jun
Chen, Hao
Liu, Tuozhen
Ye, Xianbin
Tang, Xin
Fang, Rui
Gao, Peng
Xie, Wenfeng
Xie, Guotong
author_facet Qiao, Yixuan
Zhao, Shanshan
Wang, Jun
Chen, Hao
Liu, Tuozhen
Ye, Xianbin
Tang, Xin
Fang, Rui
Gao, Peng
Xie, Wenfeng
Xie, Guotong
contents This paper describes the PASH participation in TREC 2021 Deep Learning Track. In the recall stage, we adopt a scheme combining sparse and dense retrieval method. In the multi-stage ranking phase, point-wise and pair-wise ranking strategies are used one after another based on model continual pre-trained on general knowledge and document-level data. Compared to TREC 2020 Deep Learning Track, we have additionally introduced the generative model T5 to further enhance the performance.
format Preprint
id arxiv_https___arxiv_org_abs_2205_11245
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking
Qiao, Yixuan
Zhao, Shanshan
Wang, Jun
Chen, Hao
Liu, Tuozhen
Ye, Xianbin
Tang, Xin
Fang, Rui
Gao, Peng
Xie, Wenfeng
Xie, Guotong
Information Retrieval
Computation and Language
This paper describes the PASH participation in TREC 2021 Deep Learning Track. In the recall stage, we adopt a scheme combining sparse and dense retrieval method. In the multi-stage ranking phase, point-wise and pair-wise ranking strategies are used one after another based on model continual pre-trained on general knowledge and document-level data. Compared to TREC 2020 Deep Learning Track, we have additionally introduced the generative model T5 to further enhance the performance.
title PASH at TREC 2021 Deep Learning Track: Generative Enhanced Model for Multi-stage Ranking
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2205.11245