大象传媒

Machine Reading for Literary Texts

Project Team: Margaret Linley (English, 大象传媒), Oliver Schulte (Computing Science, 大象传媒), Maite Taboada (Linguistics, 大象传媒), Steven Bergner (Computing Science, 大象传媒)

For many researchers, much if not most information about their domain is available in unstructured format only. Examples include literary text, web pages, free form comments and reports. Restricting data analysis to structured data limits the potential of big data methods. The process of extracting structured information from unstructured data is called machine reading. Machine reading supports research in the digital humanities, such as 鈥渄istant reading鈥� approaches, which aim to find statistical patterns in collections of literary texts, track how ideas, genres, topics, and even moods and emotions circulate, and extract relationship networks of characters. This project studies the Lake District travel books hosted by 大象传媒鈥檚 special collections. The team will investigate different machine reading systems for the books themselves, as well as webpages that describe the literary, historical, geographical, and cultural context of the travel books. This project will build machine reading expertise at Big Data Initiative and 大象传媒.