A Factoid based Question Answering System based on Dependency Analysis and Wikidata

Over the last years, the use and the need for automated question answering systems have become more important than ever. The main reasons for this relate to the constant increase of the information that is available in textual form as well as the need to facilitate users in getting information they seek in a precise, fast, and easy way. In this work, we deal with the problem of the open domain factoid-based answering of questions, where the answer to a question is in the form of a word or a small phrase. We present an efficient methodology for analyzing questions and specifying proper answers with the use of knowledge bases. Initially, given a specific question that a user sets, a high-quality linguistic analysis of the question is performed. The dependencies of the question are specified, and the main triplets of the question are created. The system creates a SPARQL query to get the right answer for the question via the API from the Wikidata Query Service. The results are quite encouraging and highlight the quite good performance of our methodology.