Convolutional-Match Networks for Question Answering

In this paper, we present a simple, yet effective, attention and memory mechanism that is reminis- cent of Memory Networks and we demonstrate it in question-answering scenarios. Our mechanism is based on four simple premises: a) memories can be formed from word sequences by using convo- lutional networks; b) distance measurements can be taken at a neuronal level; c) a recursive soft- max function can be used for attention; d) extensive weight sharing can help profoundly. We achieve state-of-the-art results in the bAbI tasks, outper- forming Memory Networks and the Differentiable Neural Computer, both in terms of accuracy and stability (i.e. variance) of results.