面向中文微博的评价对象与评价词语联合抽取

深入挖掘微博内容中评价对象与评价词语的词法特征、句法特征、语义特征以及相对位置特征，提出评价对象与评价词语的序列化联合抽取模型。进一步结合微博间转发关系特性提出基于转发关系的联合抽取优化算法。并与相关算法进行实验对比，对实验结果进行了综合分析，证明了方法的可行性和优越性。

Co-Extracting Opinion Targets and Opinion-Bearing Words in Chinese Micro-Blog Texts

Using lexical,syntactic,semantic and relative position features to extract opinion pairs in micro-blog,we put forward the co-extracting model,and then give co-extracting opinion pairs opti-mization algorithm based on forwarding between micro-blogs.According to the experimental results,our two-stage approach greatly improves the performances of co-extracting opinion pairs.