The past two decades have seen impressive progress in a var iety of areas of AI, particularly NLP, through the application of machine learning methods to a wide range of tasks. While deep learning is opening up exciting new approaches to longstanding, difficul t problems in computational linguistics, it also r aises important foundational questions. Specifical ly, we do not have a clear formal understanding of why multi-level recursive deep neural networks ac hieve the success in learning and classification t hat they are delivering. It is also not obvious wh ether they should displace more traditional, logic ally driven methods, or be combined with them. Fin ally, we need to explore the extent, if any, to wh ich both logical models and machine learning metho ds offer insights into the cognitive foundations o f natural language.
\n\nThe Conference on Logic and Machine Learning in Natural Language wil l address these questions and related issues. It w ill feature invited talks by leading researchers i n both fields, and high level contributed papers s elected through open competition and rigorous revi ew. Our aim is to initiated a genuine dialogue bet ween these two approaches, where they have traditi onally remained separate and in competition.
\nWe anticipate accepting 17 paper s for oral presentation, and up to 20 papers for p oster presentation.
\n