Question Dependent Recurrent Entity Network for Question Answering
This work addresses the problem of improving reasoning in question answering for AI systems, representing an incremental advancement by modifying an existing memory network.
The paper tackles question answering by introducing a neural network architecture that extends the Recurrent Entity Network to incorporate question aspects during memorization, achieving state-of-the-art results on the bAbI dataset and competitive performance on the CNN & Daily News dataset.
Question Answering is a task which requires building models capable of providing answers to questions expressed in human language. Full question answering involves some form of reasoning ability. We introduce a neural network architecture for this task, which is a form of $Memory\ Network$, that recognizes entities and their relations to answers through a focus attention mechanism. Our model is named $Question\ Dependent\ Recurrent\ Entity\ Network$ and extends $Recurrent\ Entity\ Network$ by exploiting aspects of the question during the memorization process. We validate the model on both synthetic and real datasets: the $bAbI$ question answering dataset and the $CNN\ \&\ Daily\ News$ $reading\ comprehension$ dataset. In our experiments, the models achieved a State-of-The-Art in the former and competitive results in the latter.