Using @Twitter Conventions to Improve #LOD-Based Named Entity Disambiguation
Using @Twitter Conventions to Improve #LOD-Based Named Entity Disambiguation
复制标题
使用 @Twitter 约定来改进
DOI：
--
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Kalina Bontcheva
中科院分区：
文献类型：
--
作者：
G. Gorrell;Johann Petrak;Kalina Bontcheva
最先进的命名实体消歧方法往往在社交媒体内容上表现不佳，特别是微博。推特被单独处理，更丰富的、微博特有的上下文在很大程度上被忽略了。本文重点具体量化实体消歧性能的影响时，现成的上下文信息包括从URL内容，哈希标签定义，和Twitter的用户配置文件。特别是，包含URL内容可以显著提高性能。类似地，@提及的用户简档信息将召回率提高了超过10%。对精度没有不利影响。我们还共享了一个新的tweets语料库，这些tweets都是用DBpedia URI手工注释的，注释者之间的一致性很高。
State-of-the-art named entity disambiguation approaches tend to perform poorly on social media content, and microblogs in particular. Tweets are processed individually and the richer, microblog-specific context is largely ignored. This paper focuses specifically on quantifying the impact on entity disambiguation performance when readily available contextual information is included from URL content, hash tag definitions, and Twitter user profiles. In particular, including URL content significantly improves performance. Similarly, user profile information for @mentions improves recall by over 10i¾?% with no adverse impact on precision. We also share a new corpus of tweets, which have been hand-annotated with DBpedia URIs, with high inter-annotator agreement.
影响因子：
8.6
作者：
Derczynski, Leon;Maynard, Diana;Bontcheva, Kalina
通讯作者：
Bontcheva, Kalina
回复：“使用数值方法设计模拟：重新审视平衡截距”。
影响因子：
5
作者：
Zivich,PaulN;Ross,RachaelK
通讯作者：
Ross,RachaelK