I lead the Natural Language Processing (NLP) Group at HITS gGmbH, Heidelberg, Germany. There, I am involved in NLP related projects, work with the computational linguists at HITS, and supervise PhD. students. In addition, I am Honorarprofessor in the Computational Linguistics Department at the University of Heidelberg.
Long paper accepted at EMNLP '16: Daraksha Parveen, Mohsen Mesgar and Michael Strube: Generating Coherent Summaries of Scientific Articles Using Coherence Patterns.
Long paper accepted as oral presentation at ACL '16: Nafise Sadat Moosavi and Michael Strube: Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric.
Two papers accepted at NAACL '16: Mohsen Mesgar and Michael Strube: Lexical Coherence Graph Modeling by Word Embeddings (long paper) and Nafise Moosavi and Michael Strube: Search Space Pruning: A Simple Solution for Better Coreference Resolvers (short paper).
I am (co-)area chair for (believe it or not, I'm serious) Summarization, Generation, Discourse, and Dialogue at EMNLP '16 held in Austin, Texas, November 2-6, 2016.
I was PC Co-Chair at the ACL's 2015 flagship conference ACL-IJCNLP '15 held in Beijing, China, July 26-31, 2015.
Paper accepted in TACL: Sebastian Martschat and Michael Strube: Latent Structures for Coreference Resolution (PDF).
I am member of a new research training group funded by DFG: AIPHES (Adaptive Information Processing from Heterogeneous Sources). This is a collaboration between the CS Department at the Technical University of Darmstadt, the Institute for Computational Linguistics at the University of Heidelberg and the NLP Group at HITS. I'll focus on concept disambiguation in relation with discourse processing and sentiment analysis.
Recent invited talks: At the LSDsem '15 and the CORBON '16 workshops: "The (Non-)Utility of Semantics for Coreference Resolution" (LSDsem, CORBON Remix). At the University of Mannheim, School of Business Informatics and Mathematics (and a few other places ...): "The Dark Side of NLP: An Introduction into Natural Language Processing for Spooks, Stalkers, and other Scoundrels" (PDF, Announcement). At the University of Edinburgh, Institute for Language, Cognition and Computation: "Issues I Don't Understand About Coreference and Coherence".
Teaching winter term 2016: The Dark Side of NLP: Gefahren automatischer Sprachverarbeitung in the CL Department at the University of Heidelberg.
(This isn't really news ...) According to Google Scholar the AAAI '06 and AAAI '07 papers Simone Paolo Ponzetto and I co-authored are the most cited papers of the top conference in AI (Google Scholar query for AAAI 2006 and AAAI 2007)!
Linguistics:
Computational Linguistics:
Natural Language Processing:
Publications in Journals and Books, Conference Proceedings, Workshop Proceedings, and Complete List of Publications
See my publications at Google Scholar.
Send me email if you want to get a copy of a paper not linked on these pages (in those cases we had to transfer the copyright to the respective publishers; maybe linguists should follow the good example of JAIR and start to publish in open access journals).
I received my Ph.D. from the (now defunct) Computational Linguistics Department at the University of Freiburg, Germany, in December 1996 under the supervision of Udo Hahn. Between 1997 and 1999 I was a postdoctoral fellow at the Institute for Research in Cognitive Science at the University of Pennsylvania, Philadelphia, PA. In 2000 I joined the European Media Lab in Heidelberg, Germany, as a researcher. Since 2001 I am group leader of the Natural Language Processing (NLP) Group of HITS, an institute which rapidly underwent several transformations before (hopefully) arriving at its final destination:
European Media Lab → EML Research → HITS.
Anyway, it has been a lot of fun to be here ...
In 2010 I got appointed Honorarprofessor in the Computational Linguistics Department at the University of Heidelberg.
In 2015/16 I serve as deputy scientific director at HITS.
In 2015 I was PC Co-Chair of the ACL's flagship conference ACL-IJCNLP '15 held in Beijing, China, July 26-31, 2015. We created about 3000 pages of printed paper as output.
