课程介绍

From social media to news articles to machine logs, text data is everywhere. In this class, you'll learn how to do text analytics, also known as Information Extraction: how to extract structured data from text in order to derive valuable insights. You will learn about applications of information extraction in many domains: social media analytics, healthcare analytics, financial risk analysis and many others, and common tasks: extracting entities and relations between them, event extraction and sentiment analysis. You'll then dive into "Declarative Information Extraction", a powerful method to building high-performance and high-quality text analytics, and gain hands-on experience writing your own extractors with a tool called SystemT (available as IBM BigInsights Text Analytics).

课程大纲

考核标准

课件浏览100%,客观练习0%,主观练习0%,课内讨论0%。
课程内容不断迭代，成绩以当时的课程内容为准，一旦合格，可以申请证书。申请证书后，以结课处理，成绩不再改动