Natural Language Processing (NLP)

The Natural Language Processing (NLP) group develops methods, algorithms, and tools for the automatic analysis of natural language. The group focuses on questions related to processing, understanding and generating discourse. It works on coreference resolution with a particular focus on appropriate representations for the task. It develops models of local coherence, most recently an unsupervised, graph-based version of the entity grid with applications in text generation, assessing readability and automatic summarization. The group is also interested in word sense disambiguation and its relations to discourse processing.


Successful defense

Benjamin Heinzerling from the NLP group has successfully defended his PhD thesis with the title “Aspects of Coherence for Entity Analysis”. Benjamin used to work in the DFG-funded research training group AIPHES and will soon take on a post-doc position at RIKEN AIP / Tohoku University, Sendai, Japan.


The SCAD Project (Scalable Author Disambiguation for Bibliographic Databases), which has been funded by the Leibniz-Gemeinschaft and the Klaus-Tschira-Foundation, will have a dedicated Deep Dive session at GNDCon2018, which will be held by the German National Library on December 3rd and 4th, 2018, in Frankfurt. With our project partners DBLP and Zentralblatt MATH, we will…


ACM Symposium 2018: Michael Strube speaks about „the dark side of NLP“

The German Chapter of the Association for Computing Machinery (ACM) turns 50 this year and celebrates its anniversary with a Symposium in Heidelberg. The Symposium takes place 20-21 September 2018 under the motto “Being Human with Algorithms”. Experts from all over the world discuss effects of the digital transformation to modern society – including all its side effects. The talks range from topics of digitalization, artificial intelligence, autonomous driving, over big data to blockchain, and more.