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.



Two papers got accepted at NAACL-HLT 2016: Nafise Moosavi and Michael Strube: Search Space Pruning: A Simple Solution for Better Coreference Resolvers (short paper), and Mohsen Mesgar and Michael Strube: Lexical Coherence Graph Modeling By Word Embeddings (long paper).

Another PhD. Thesis Defended

Yufang Hou (second from the left, with her examination committee) has successfully defended her PhD. thesis on “Unrestricted Bridging Resolution”. Yufang, a former HITS doctoral student who also worked at the ICL Computational Linguistics Group in Heidelberg, is now with IBM Research in Ireland.

EMNLP 2016

Michael Strube will be Area Co-Chair for Summarization, Generation, Discourse, and Dialogue at EMNLP ’16 to be held in Austin, TX, USA, November 2-6, 2016.