Simple and Effective Question Answering with Recurrent Neural Networks

First-order factoid question answering assumes that the question can be answered by a single fact in a knowledge base (KB). While this does not seem like a challenging task, many recent attempts that apply either complex linguistic reasoning or deep neural networks achieve 35%-65% on benchmark sets. Our approach formulates the task as two machine learning problems: detecting the entities in the question, and classifying the question as one of the relation types in the KB. Based on this assumption of the structure, our simple yet effective approach trains two recurrent neural networks to outperform state of the art by significant margins --- relative improvement reaches 16% for WebQuestions, and surpasses 38% for SimpleQuestions.