“Question answering from semi-structured resources”- Summer 2017

We study how natural language processing and information access methods can improve human-computer interaction. Wikipedia, the world’s largest crowdsourced encyclopedia, is a great source of knowledge for question answering systems. Using Wikipedia, we hope to considerably increase the precision and coverage of our START Natural Language Question Answering System (start.mit.edu). In particular, we are building systems to structure knowledge in Wikipedia and other websites, turning them into a virtual database accessible via natural language. Your work will help the START system answer thousands of new questions every day.
Good candidates are passionate about well-designed code, are interested in learning new programming languages, and have experience with large codebases and Test Driven Development. Exposure to linguistics and Knowledge of Lisp or Scheme is a plus.
Contact: Sue Felshin (sfelshin@csail.mit.edu)