Almost all of today’s knowledge is stored in databases and thus can only be accessed with the help of domain specific query languages, strongly limiting the number of people which can access the data. In this work, we demonstrate an end-to-end trainable question answering (QA) system that allows a user to query an external NoSQL database by using natural language. A major challenge of such a system is the non-differentiability of database operations which we overcome by applying policy-based reinforcement learning. We evaluate our approach on Facebook’s bAbI Movie Dialog dataset and achieve a competitive score of 84.2% compared to several benchmark models. We conclude that our approach excels with regard to real-world scenarios where knowledge resides in external databases and intermediate labels are too costly to gather for non-end-to-end trainable QA systems.

Finding reliable train connections is a considerable issue in timetable information since train delays perturb the timetable daily. We present an effective probabilistic approach for estimating the reliability of connections in a large train network. Experiments on real customer queries and real timetables for all trains in Germany show that our approach can be implemented to deliver good results at the expense of only little processing time. Based on probability distributions for train events in connections, we estimate the reliability of connections. We have analyzed our computed reliability ratings by validating our predictions against real delay data from German Railways. This study shows that we are able to predict the feasibility of connections very well. In essence, our predictions are slightly optimistic for connections with a high rating and pretty accurate for connections with a medium rating. Only for the rare cases of a very low rating, we are too pessimistic. Our probabilistic approach already delivers good results, still has improvement potential, and offers a new perspective in the search for more reliable connections in order to bring passengers safely to their destinations even in case of delays.