很久没有看论文了,今天看一下“life event identification using semantic and syntactic graph”。
问题:generate brief automated biographies for the users based on their generated content
困难: amount,mention a life event or just same theme
方法:uni-gram - 分类效果不错,但是不能识别文本是提到生活事件或是描述生活(没有足够的语义信息)
semantic and syntactic graph - 文本(wordnet,conceptnet)和语法结构(dependency parsing)——》frequent pattern mining,extract feature -> classifiers
过程:expands a Twitter post into both a syntactic and semantic graph;mined for frequent sub patterns;classifier,
描述:description,semantic-> classify theme ; syntactic -> post in the past or not
semantic -> conceptNet and word Net
syntactic -> dependency and tokens graph
frequent pattern -> CloseGraph
Experiment:
classifier:LibLinear
feature reduction:Weka
feature combine:N-Grams, Entities, Topics, Syntactic, Semantic ConceptNet, and Semantic WordNet),
presented a new approach for the problem of life event detection that focusses on five major life
events identified
总结,这篇文章并不是很有开创性,但是解决的问题的思路和方法还是很有可取,同时考虑了语义和语法(这是常见套路?),解题思路上都用的常规的方法(所以导致没法发表的太好,没有科学问题????),对比实验很多,结果也可以,但是仅仅作为分类器,分类的类别仅有5大类,语义分析还是不足的。