Research Project Title:
Fact Checking and Reasoning
abstract:Our goal is to develop an automated solution which accomplishes three tasks: 1) It should, given some document, differentiate which sentences are making substantive claims that require verification, and which do not, 2) It should, given some sentence, detect whether it agrees or disagrees with some evidence. One example could be: given the evidence “The bear scared off the baby that was attacking him”, does it agree or disagree with the claim “The bear is scary”. 3) It should be able to, given some claim, provide evidence from a large corpus (example: Wikipedia) that agrees or disagrees with that claim. For example, given the claim “The bear is scary”, it should be able to provide documents that prove/disprove this claim.
"I'm participating in SuperUROP because it'll help provide a great venue to do some substantial research at MIT. I felt sufficiently prepared by a combination of classes and side projects. I hope to learn a lot about the state of Natural Language Processing research; particularly, its applications on industry. Fake News is also something that really excites me, and I couldn't be more grateful to work on it."