Automatic Rule Generation and Generalization for an Information Extraction System Using MAXIM

Many recent information extraction (IE) systems have ignored the tedious and timeconsuming nature of the preparation involved in using them. The abundance of graduate students has eased the pain of providing annotated corpora, pre-filled answer templates, and manual examination of automatically-generated rules and final answers. In this paper, we present a new system comprised of previously published solutions to different aspects of IE in an effort to automate as much of the task as possible while achieving competitive results.