文章预览
引言 命名实体识别是自然语言处理中一个非常基础的工作,是自然语言处理中关键的一个环节。监督学习是解决命名实体识别任务的一个基本手段,但标注数据的获取成本往往会比较高,本期PaperWeekly将带大家来看一下如何通过半监督或者无监督的方法来做命名实体识别任务。本期分享的4篇Paper Notes分别是: 1、Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre), 2016 2、ClusType: Effective Entity Recognition and Typing by Relation Phrase-Based Clustering, 2015 3、Bootstrapped Text-level Named Entity Recognition for Literature, 2016 4、Recognizing Named Entities in Tweets, 2011 Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre) 作者 Lifu Huang, Jonathan May, Xiaoman Pan, Heng Ji 单位 Re
………………………………