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 Paper Accepted

A paper by Daraksha Parveen, PhD. student in the HITS NLP group, has been accepted at EMNLP ’16. The title of the long paper, which is co-authored by Mohsen Mesgar and Michael Strube, is ‘Generating Coherent Summaries of Scientific Articles Using Coherence Patterns’.

ACL 2016

A paper by Nafise Sadat Moosavi, PhD. student in the HITS NLP group, has been accepted as a long paper at ACL 2016: Nafise Sadat Moosavi and Michael Strube: Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric. The paper comes with a coreference scorer implementation that will be…