Ten papers from UKP co-authors have been accepted for publication at EMNLP 2018, the 2018 Conference on Empirical Methods in Natural Language Processing. The conference will take place in Brussels, Belgium, from October 31st through November 4th, 2018.

Long papers:

• A Neural Local Coherence Model for Text Quality Assessment
  Mohsen Mesgar and Michael Strube
• APRIL: Interactively Learning to Summarise by Combining Active Preference Learning and Reinforcement Learning
  Yang Gao, Christian M. Meyer and Iryna Gurevych
• Cross-topic Argument Mining from Heterogeneous Sources
  Christian Stab, Tristan Miller, Benjamin Schiller, Pranav Rai and Iryna Gurevych
• Data Augmentation via Dependency Tree Morphing for Low-Resource Languages
  Şahin, Gözde Gül and Steedman, Mark
• Investigating Capsule Networks with Dynamic Routing for Text Classification
  Wei Zhao, Jianbo Ye, Min Yang, Zeyang Lei, Suofei Zhang and Zhou Zhao
• Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks
  Steffen Eger, Paul Youssef and Iryna Gurevych
• Using Linguistic Features to Improve the Generalization Capability of Neural Coreference Resolvers
  Moosavi, Nafise Sadat and Strube, Michael
• Weeding out Conventionalized Metaphors: A Corpus of Novel Metaphor Annotations
  Erik-Lân Do Dinh, Hannah Wieland and Iryna Gurevych

System Demonstration papers:

• Integrating Knowledge-Supported Search into the INCEpTION Annotation Platform
  Beto Boullosa, Richard Eckart de Castilho, Naveen Kumar, Jan-Christoph Klie and Iryna Gurevych
• Interactive Instance-based Evaluation of Knowledge Base Question Answering
  Daniil Sorokin and Iryna Gurevych