Proceedings of the 2nd Workshop on Deriving Insights from User-Generated Text

Welcome to the 2nd WIT (Workshop On Deriving Insights From User-Generated Text)! Recent advances in Conversational AI, Natural Language Processing, Natural Language Understanding, Language Generation, Machine Learning, Deep Learning, Knowledge Bases, and others, have demonstrated promising results and far-reaching uses of text. Such results can be seen in many different tasks including, but not limited to better extractions from user-generated content, better language models, new approaches related to (commonsense) knowledge-bases, knowledge graphs, better information seeking QA (or Dialogue) systems, etc. Classical data management problems such as data cleaning/integration and search may also benefit from these new approaches. The WIT workshop series was started to provide a venue to exploit and explore the use of advanced AI/ML/NLP techniques on user-generated text, which is rich in user insights and experiences. Therefore, the goal of this workshop series is to bring together researchers interested in the development and the application of novel approaches/models/systems to address challenges around harnessing text-heavy user-generated data that is available to organizations and over the Web. For this 2nd edition, the workshop will have a great line-up of invited speakers (Mirella Lapata-University of Edinburgh, Rada Mihalcea-University of Michigan, Ann Arbor, Nina Balcan-Carnegie Mellon University, Carlos Guestrin-Stanford University) as well oral (and poster) presentations of contributed research papers. Following the tradition started in the 1st WIT, the 2nd WIT will host a panel of experts from …