Micro-blogs Entity Recognition Based on DSTCRF

We proposed a unified model for Chinese named entity recognition in micro-blogs. The models provide a simple statistical framework to incorporate a wide variety of linguistic knowledge and statistical models in a unified way. In our approach, KNN classifier is used to get suitable training data. An optimal algorithm to generate the hierarchically structured DSTCRF is executed to select the structure attributes of the named entity in micro-blogs knowledge. The experimental results showed that the accuracy rate was significantly improved.