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.


EMNLP 2014

Two long papers accepted at EMNLP ’14: Yufang Hou, Katja Markert and Michael Strube: A rule-based system for end-to-end bridging resolution, and Sebastian Martschat and Michael Strube: Recall error analysis for coreference resolution.


Long paper accepted for oral presentation at COLING ’14: Nafise Sadat Moosavi and Michael Strube: Unsupervised coreference resolution by utilizing the most informative relations.

DFG funds an interdisciplinary Research Training Group

DFG funds an interdisciplinary Research Training Group (DFG Graduiertenkolleg) “Adaptive Information Processing from Heterogeneous Sources” in a cooperation of TU Darmstadt, Heidelberg University, and Heidelberg Institute for Theoretical Studies . The German Research Foundation will fund a new interdisciplinary research training group “Adaptive Information Processing from Heterogeneous Sources”. This research training group will be jointly…