MIT | IBM-Watson AI Undergraduate Research and Innovation Scholar
Linguistic Analysis of Wikipedia for Question Answering
- Natural Language and Speech Processing
I will be working with the Infolab group to contribute to further development of their START Natural Language Question Answering System. The overall goal is to increase the precision and coverage of this system using natural language processing and linguistic analysis of information from Wikipedia and other similar resources. Specifically, I will be working on an existing codebase that uses Wikipedia infoboxes and other structured data to parse information useful for natural language question answering. This will consist of a lot of database work that will help with START’ s ability to parse questions and come up with concise, helpful answers.
I am participating in SuperUROP to learn more about what it’s like to work as a researcher. I’m thinking about going to grad school, and I look forward to getting more research experience through SuperUROP. I’ve enjoyed all the classes I’ve taken at MIT about machine learning, but I haven’t had much exposure to natural language processing specifically, so I’m excited to learn more through my research.