Pretraining De-Biased Language Model with Large-scale Click Logs for Document Ranking
Xiangsheng Li, Xiaoshu Chen, Kunliang Wei, Bin Hu, Lei Jiang, Zeqian Huang, Zhanhui Kang
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/lixsh6/tencent_wsdm_cup2023OfficialIn paperpytorch★ 23
Abstract
Pre-trained language models have achieved great success in various large-scale information retrieval tasks. However, most of pretraining tasks are based on counterfeit retrieval data where the query produced by the tailored rule is assumed as the user's issued query on the given document or passage. Therefore, we explore to use large-scale click logs to pretrain a language model instead of replying on the simulated queries. Specifically, we propose to use user behavior features to pretrain a debiased language model for document ranking. Extensive experiments on Baidu desensitization click logs validate the effectiveness of our method. Our team on WSDM Cup 2023 Pre-training for Web Search won the 1st place with a Discounted Cumulative Gain @ 10 (DCG@10) score of 12.16525 on the final leaderboard.