Artificial Intelligence for Question Answering - ADBIS Workshop

Introduction The 1st Workshop on Articial Intelligence for Question Answering (AI*QA 2018) has been organised by Ermelinda Oro and Massimo Ruffolo (National Research Council, Italy), and Eduardo Ferme (University of Madeira,Funchal, Portugal). Articial Intelligence (AI) is attracting much attention. It will be a major driver for technology changes that will deeply impact how we live and work. Question Answering (QA), which has the goal to automatically provide pertinent answers to natural language questions, is a complex task that requires contextual natural language understanding (NLU), and reasoning abilities. Almost all Natural Language Processing (NLP) tasks can be seen as a QA problem (e.g. entity extraction, sentiment analysis, machine translation). Recently, QA based on novel AI techniques has seen scientic and commercial popularity that attracted media attention, but eective QA is a challenging task for machines that try to simulate the human behaviour. Some solutions are based on Information Retrieval (IR) techniques, other on Information Extraction (IE) processes that enable to create Knowledge Bases (KBs), so logic-based query languages are used to infer answers from KBs. Novel approaches for QA over documents are based on Deep Neural Networks that encode the documents and the questions to determine the answers. A lot of research has focused on learning from fixed training sets of labeled data, but other try to learn through online interaction (dialogue) with humans or other agents. The purpose of the AI*QA workshop is to bring together researchers, engineers, and practitioners interested in the theory and applications related to QA problems by using AI techniques. The aim is to better understand the advantages and the limitations of proposed solutions and systems in dierent domains and situations by stimulating and facilitating through the workshop an active exchange, interaction, and comparison of approaches, methods, tools, and ideas. Topics of interest include the following categories: theoretical models for answering questions, algorithms and methods, databases and knowledge representations, tools and solutions, evaluation of results, application to domains.