MMM
YYYY
Modeling Relevance Ranking under the Pre-training and Fine-tuning Paradigm
预训练和微调范式下的相关性排序建模
事前訓練と微調整パラダイム下の関連性ランキングのモデリング
예비 훈련 과 마이크로 모드 에서 의 상관 성 정렬 모델 링
Modelo de orden de correlación basado en paradigmas de pre - entrenamiento y ajuste fino
Modélisation de l'ordre de corrélation basée sur le paradigme de pré - formation et de réglage fin
модель ранжирования по типу ранжирования
Lin Bo ¹, Liang Pang 庞亮 ³, Gang Wang ⁴, Jun Xu 徐君 ², XiuQiang He 何秀强 ⁴, Ji-Rong Wen 文继荣 ²
¹ School of Information, Renmin University of China, Beijing, China
中国 北京 中国人民大学信息学院
² Gaoling School of Artificial Intelligence, Renmin University of China, , Beijing, China
中国 北京 中国人民大学高瓴人工智能学院
³ Institute of Computing Technology, Chinese Academy of Sciences
中国 北京 中国科学院计算技术研究所
⁴ Huawei Noah’s Ark Lab
中国 香港 华为诺亚方舟实验室
arXiv, 12 August 2021
Abstract

Recently, pre-trained language models such as BERT have been applied to document ranking for information retrieval. These methods usually first pre-train a general language model on an unlabeled large corpus and then conduct ranking-specific fine-tuning on expert-labeled relevance datasets. Though reliminary successes have been observed in a variety of IR tasks, a lot of room still remains for further improvement.

Ideally, an IR system would model relevance from a user-system dualism: the user's view and the system's view. User's view judges the relevance based on the activities of “real users” while the system's view focuses on the relevance signals from the system side, e.g., from the experts or algorithms, etc. Inspired by the user-system relevance views and the success of pre-trained language models, in this paper we propose a novel ranking framework called Pre-Rank that takes both user's view and system's view into consideration, under the pre-training and fine-tuning paradigm. Specifically, to model the user's view of relevance, Pre-Rank pre-trains the initial query-document representations based on a large-scale user activities data such as the click log. To model the system's view of relevance, Pre-Rank further fine-tunes the model on expert-labeled relevance data. More importantly, the pre-trained representations, are fine-tuned together with handcrafted learning-to-rank features under a wide and deep network architecture. In this way, Pre-Rank can model the relevance by incorporating the relevant knowledge and signals from both real search users and the IR experts.

To verify the effectiveness of Pre-Rank, we showed two implementations by using BERT and SetRank as the underlying ranking model, respectively. Experimental results base on three publicly available benchmarks showed that in both of the implementations, Pre-Rank can respectively outperform the underlying ranking models and achieved state-ofthe-art performances. The results demonstrate the effectiveness of Pre-Rank in combining the user-system views of relevance.
arXiv_1
arXiv_2
arXiv_3
arXiv_4
Reviews and Discussions
https://www.hotpaper.io/index.html
Parametric study on the flutter sensitivity of a wide-chord hollow fan blade
Influence of aspect ratio and arrangement direction on the shear behavior of ellipsoids
Development of a double-layer shaking table for large-displacement high-frequency excitation
Effect of SiC Particle Size on Properties of SiC Porous Ceramics
Physical Layer Authentication in UAV-enabled Relay Networks Based on Manifold Learning
Risk assessment of fault water inrush during deep mining
Simvastatin Improves Outcomes of Endotoxin-induced Coagulopathy by Regulating Intestinal Microenvironment
Sound Insulation Performance of Pyramidal Truss Core Cylindrical Sandwich Structure
Coupling analysis of passenger and train flows for a large-scale urban rail transit system
Effects of minor B additions on tensile strength, fracture toughness and oxidation resistance of Nb–Si based alloys
Essential role of MALAT1 in reducing traumatic brain injury
Seasonal Cumulative Effect of Ural Blocking Episodes on the Frequent Cold events in China during the Early Winter of 2020/21



Previous Article                                Next Article
About
|
Contact
|
Copyright © Hot Paper