Author name disambiguation using a graph model with node splitting and merging based on bibliographic information
Author name disambiguation using a graph model with node splitting and merging based on bibliographic information
1. 概述
2. 创新点
3. 整体框架

3.1. Graph Model Constructor


3.2. Namesake Resolver
3.2.1. Cycle Detector

3.2.2. Namesake Splitter
3.3. Heteronymous Name Resolver
3.3.1. similar name searcher
3.3.2. same author detector
3.3.3. heteronymous name merger
3.4. Outlier Remover

4. Experiment

- 对比使用了哪些属性,信息缺失是否严重
- 如何定义相似性阈值


- 使用所有特征属性(合著者,title,地点)
- 在 arnet 上比 GFAD 性能好
- 需要预先定义标题和地址的相似度阈值
- 选择一个唯一的不变的阈值不太现实
- 仅使用共同作者
5. GFAD 局限性
Author name disambiguation using a graph model with node splitting and merging based on bibliographic information的更多相关文章
- 推荐系统中的Graph Model
转自:http://www.cnblogs.com/wentingtu/archive/2012/05/28/2521166.html 推荐中对graph model的研究主要有两个方面,一个是如何构 ...
- factor graph model
主实验 文慧:用户,商品,评分,review,ranking. 数据集:数据规模,论文源代码
- Fast Token Replacement in C#
http://www.codeproject.com/Articles/298519/Fast-Token-Replacement-in-Csharp Fast Token Replacement i ...
- 讲座:Influence maximization on big social graph
Influence maximization on big social graph Fanju PPT链接: social influence booming of online social ne ...
- Django文档——Model中的ForeignKey,ManyToManyField与OneToOneField
关联关系字段 (Relationship fields) ForeignKey,ManyToManyField与OneToOneField分别在Model中定义多对一,多对多,一对一关系. 例如,一本 ...
- 论文笔记:Person Re-identification with Deep Similarity-Guided Graph Neural Network
Person Re-identification with Deep Similarity-Guided Graph Neural Network 2018-07-27 17:41:45 Paper: ...
- 【论文笔记】Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition 2018-01-28 15:4 ...
- [Windows Azure] Using the Graph API to Query Windows Azure AD
Using the Graph API to Query Windows Azure AD 4 out of 4 rated this helpful - Rate this topic This d ...
- DeepLearning - Overview of Sequence model
I have had a hard time trying to understand recurrent model. Compared to Ng's deep learning course, ...
随机推荐
- [洛谷P4822][BJWC2012]冻结
题目大意:有一张$n(n\leqslant50)$个点$m(m\leqslant1000)$条边的无向图,可以使得$k$条边使得边权减半,求最短路 题解:分层图最短路 卡点:无 C++ Code: # ...
- 【Codeforces Round #406 (Div. 2)】题解
The Monster 签到题,算一下b+=a和d+=c,然后卡一下次数就可以了. Not Afraid 只要一组出现一对相反数就是安全的. Berzerk 题意:[1,n],两个人轮流走,谁能走到1 ...
- 洛谷2219:[HAOI2007]修筑绿化带——题解
https://www.luogu.org/problemnew/show/P2219#sub 为了增添公园的景致,现在需要在公园中修筑一个花坛,同时在画坛四周修建一片绿化带,让花坛被绿化带围起来. ...
- [Leetcode] combination sum ii 组合之和
Given a collection of candidate numbers ( C ) and a target number ( T), find all unique combinations ...
- 淘淘相关DTO
result 用于Controller层返回值或Controller于service层之间返回值 package com.taotao.common.pojo; import java.util.Li ...
- [freemarker篇]06.超级强大的自定义指令
Freemarker的自定义指令是很强大的,非常强大,在之后的教程中我会简单的做一个示例,让大家对其有所了解!如果做Freemarker编程,请好好看看API手册,可以说里面的内容很多!也是一门独立的 ...
- Java的Comparable接口的一个陷阱
转载自:http://my.oschina.net/jack230230/blog/56339 Java的Comparable接口提供一个对实现了这个接口的对象列表进行排序的办法.原始的排序对于简单的 ...
- 2015/9/15 Python基础(12):模块和包
模块是用来组织 Python 代码的方法,而包则是用来组织模块的. 当代码量很大时,我们一般会把代码分成几个有组织的代码段,然后每个代码段之间有一定的联系.代码单之间是共享的,所以Python允许调入 ...
- 优雅退出telnet
echo "" |telnet IP 端口
- Flume入门——Selector、Chanel等
1.selector (http://blog.csdn.net/looklook5/article/details/40430965) (http://blog.csdn.net/xiao_jun_ ...