欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
近年来排序学习方法以其优异的性能成为信息检索领域研究的一个热点。排序学习方法应用机器学习方法训练排序模型用于文档相关性排序，取得了良好的实验结果。在多种排序学习模型中又以Listwise方法的效果最为显著，特别是基于神经网络的排序学习算法以其良好的理论基础，灵活的损失函数构造形式，成为排序学习研究的重要手段。本文对基于神经网络的Listwise排序学习方法及其改进方法进行综述，并介绍该方面研究的最新进展。
英文摘要：
Learning to rank approach, with outstanding performance, has become a hot research issue of information retrieval. Its task is to learn a ranking model for sorting documents by relevance according to a query based on machine learning model. The performance of listwise approach is better than other learning to rank approaches, especially, the approach based on neural network is one of most important means to research the learning to rank approaches for its favorable foundations in theory and flexible construction forms of loss function. This paper summarizes the ranking neural network based approaches to introduce the latest research on this issue.
同期刊论文项目
同项目期刊论文
Web-oriented OOV translation extracting approach through cross-language query expansion for English-
BioPPISVMExtractor:A Protein-Protein Interaction Extractor for Biomedical Literature Using SVM and R
Uncertainty sampling-based active learning for protein-protein interaction extraction from biomedica
Improving the performance of bio-entity name recognition in biomedical literature via the contextual
Incorporating rich features to boost information retrieval performance: A SVM-regression based re-ra
期刊信息
位置：