Tabular data is difficult to analyze and search through. There is a clear need for new tools and interfaces that would allow even non-tech-savvy users to gain insights from open datasets without resorting to specialized data analysis tools or even having to fully understand the dataset structure. We explore the End-To-End Memory Networks architecture (Sukhbaatar et al., 2015) in application to answering natural language questions from tabular data. This architecture was originally designed for the question-answering tasks from short natural language texts (bAbI tasks) (Weston et al., 2015), which include testing elements of inductive and deductive reasoning, co-reference resolution and time manipulation.
MSc. Svitlana Vakulenko is a researcher at the Institute for Information Business at WU Wien and a PhD student in Informatics at TU Wien. Her research expertise lies in the area of machine learning for natural language processing. She has been involved in several international research projects and is currently working in CommuniData FFG project (communidata.at), which aims to enhance usability of Open Data and its accessibility for non-expert users in local communities.