Dipartimento di Ingegneria informatica, automatica e gestionale

In this paper we present a novel mechanism to get explanations that allow to better understand network predictions when dealing with sequential data. Specifically, we adopt memory-based net- works — Differential Neural Computers — to ex- ploit their capability of storing data in memory and reusing it for inference. By tracking both the mem- ory access at prediction time, and the information stored by the network at each step of the input sequence, we can retrieve the most relevant input steps associated to each prediction. We validate our approach (1) on a modified T-maze, which is a non-Markovian discrete control task evaluating an algorithm’s ability to correlate events far apart in history, and (2) on the Story Cloze Test, which is a commonsense reasoning framework for evaluat- ing story understanding that requires a system to choose the correct ending to a four-sentence story. Our results show that we are able to explain agent’s decisions in (1) and to reconstruct the most relevant sentences used by the network to select the story ending in (2). Additionally, we show not only that by removing those sentences the network predic- tion changes, but also that the same are sufficient to reproduce the inference.