In this paper, we presented an effective method to recognize product named entity from Chinese microblog. Due to the short, noisy and informal text, it is much more difficult to recognize Pro-NEs from microblog than traditional media, such as news articles. In order to work out the challenges, we carried out a statistical analysis on the appearance of Pro-NEs in Chinese microblog, According to the structure of Pro-NEs, we integrated some features and introduced external knowledge to the conditional random fields model. Experiments on an artificial annotated microblog corpus show that our approach can improve the performance of the product named entity recognition from microblog.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.