2月10日魏忠钰：News Highlights Generation using Microblogs
Dr. Zhongyu Wei is a postdoctoral fellow at University of Texas at Dallas, member of Human Language Technology Research Institute. His research areas are in natural language processing, information retrieval and data mining, with special emphasis on automatic summarization and social media. He got his Ph.D. degree from Chinese University of Hong Kong in 2014. Prior to that, he received his Bachelors and Masters degrees from Harbin Institute of Technology.
News highlights is succinct single-document summary for readers to quickly access the gist of a news article. Traditional automatic extractive approaches suffer from two problems: (1) They rely on linguistic and/or statistic features but these features are ineffective to locate highlights sentences. (2) Sentences extracted as highlights are verbose in general. We explore to use microblogs related to target news article to tackle the aforementioned problems for generating better news highlights.