Question Dependent Recurrent Entity Network for Question Answering

TL;DR

This paper introduces a neural network model called Question Dependent Recurrent Entity Network that enhances memory networks with question-aware attention for improved question answering, achieving state-of-the-art results on synthetic data and competitive results on real datasets.

Contribution

The paper proposes a novel question-dependent recurrent entity network that incorporates question information during memorization, improving reasoning capabilities in question answering models.

Findings

Achieved state-of-the-art performance on the bAbI dataset.

Obtained competitive results on CNN & Daily News reading comprehension.

Demonstrated effectiveness of question-aware attention in memory networks.

Abstract

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.