Tried
before
PIQASso and MIT systems have applied dependency relations in QA.
Used exact match of relations to extract answers directly.
Why need to consider dependency relations?
An upper bound of 70% for answer extraction (Light
et al., 2001)
Many NEs with the same type
appearing close to each other.
Some questions dont have NE-type targets.
E.g. what does AARP stand for?