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.

News

Another Successful Defense

Sebastian Martschat (second from the right, with his examination committee) has successfully defended his PhD. thesis on “Structured Representations for Coreference Resolution”. Sebastian is a former HITS doctoral student who now works as a research assistant at Heidelberg University.

New Scientific Director: Michael Strube

As of January 2017, Prof. Dr. Michael Strube is the new Scientific Director (“Institutssprecher”) of HITS. As the position of Scientific Director rotates through the group leaders, this is a planned change in the HITS management. Rebecca Wade, who was Scientific Director for the last two years, stepped down from the position at the end…

Details

EACL Paper Accepted

The paper “Trust, but Verify! Better Entity Linking through Automatic Verification” by Benjamin Heinzerling, Michael Strube, and Chin-Yew Lin has been accepted as a long paper at EACL 2017, to be held in Valencia, Spain, from April 3 – 7, 2017.