Photograph of Michael Strube

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. In 2017/18 I serve as scientific director at HITS.

 

news

In the media: The topic of our workshop on Ethics in NLP is covered by an article in the Süddeutsche Zeitung. On bias in machine learning for NLP and AI on April 22nd, 2017, in the science program Die Profis at Rundfunk Berlin-Brandenburg.

Short paper accepted at ACL '17: Nafise Sadat Moosavi and Michael Strube: Lexical Features in Coreference Resolution: To be Used With Caution.

Long paper accepted at EACL '17: Benjamin Heinzerling, Michael Strube and Chin-Yew Lin: Trust, but Verify! Better Entity Linking through Automatic Verification.

March for Science on April 22nd, 2017, in Heidelberg. Within three minutes I tried to talk about computational linguistics and computer science, their relevance for our society and our responsibility as scientists. My script in German and (roughly translated to) English. For impressions on the event, see here. As a follow-up I got invited to participate in a panel discussion on May 18th, 2017, at DKFZ Heidelberg on the future of the movement.

Recent public talks: May 15th, 2017, at the DAI Heidelberg in the series "Digitalität@Heidelberg". May 10th, 2017, at the Medienforum 2017. November 14th, 2016 at the University of Braunschweig in the series Zukunftsfragen kontrovers: Big Brother liest mit: Informationstechnologie zwischen Überwachungsstaat und gesellschaftlichem Nutzen . December 6th, 2016 at the University of Heidelberg in the series Gegenwartsliteratur und Zeitdiagnostik: Dave Eggers' Roman »The Circle« (2013). Segen und Fluch der Transparenzgesellschaft.

Recent invited talks: At the journalists' conference Netzwerk Recherche 2017 on the "Dark Side of NLP ... 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)!

 

research interests

Linguistics:

  • Text and Dialogue
  • Pragmatics

Computational Linguistics:

  • Anaphora and Coreference Resolution
  • Generation of Referring Expressions
  • Modeling Local (and maybe also Global) Coherence
  • Discourse and Dialogue Structure (though I don't believe in it)

Natural Language Processing:

  • Automatic Summarization
  • Concept Disambiguation, Entity Linking, Cross-document Coreference Resolution
  • Information Extraction
  • Knowledge Acquisition, Ontology Learning
  • Natural Language Generation Systems

 

publications

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).


A Few Recent Publications


  • Moosavi, Nafise Sadat; Strube, Michael (2017).
    Lexical Features in Coreference Resolution: To Be Used with Caution.
    In: ACL '17 (short paper), to appear.
  • Heinzerling, Benjamin; Strube, Michael; Lin, Chin-Yew (2017).
    Trust, but Verify! Better Entity Linking through Automatic Verification.
    In: EACL '17 (long paper), pp.828-838. (PDF)
  • Moosavi, Nafise Sadat; Strube, Michael (2016).
    Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric.
    In: ACL '16 (long paper), pp.632-644. (PDF)
  • Mesgar, Mohsen; Strube, Michael (2015).
    Lexical Coherence Graph Modeling by Word Embeddings.
    In: NAACL '16 (long paper), pp.1414-1423. (PDF)
  • Martschat, Sebastian; Strube, Michael (2015).
    Latent Structures for Coreference Resolution.
    In: TACL, 3, pp.405-418. (PDF)
  • Nastase, Vivi; Strube, Michael (2013).
    Transforming Wikipedia into a Large Scale Multilingual Concept Network.
    In: Artificial Intelligence, 194, pp.62-85. (DOI) (PDF)
  • Zirn, Cäcilia; Niepert, Mathias; Stuckenschmidt, Heiner; Strube, Michael (2011).
    Fine-grained Sentiment Analysis with Structural Features.
    In: IJCNLP '11, pp.336-344. (PDF)
    Best Paper Award!
  • Ponzetto, Simone Paolo; Strube, Michael (2011).
    Taxonomy Induction Based on a Collaboratively Built Knowledge Repository.
    In: Artificial Intelligence, 175 (9/10), pp.1737-1756. (PDF)
  • Ponzetto, Simone Paolo; Strube, Michael (2007).
    Knowledge Derived from Wikipedia for Computing Semantic Relatedness.
    In: Journal of Artificial Intelligence Research 30, pp.181-212. (PDF).
    Honorable Mention for the IJCAI-JAIR best paper prize 2010 (awarded to an outstanding paper published in JAIR in the preceding five calendar years).
 

short biography

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 2017/18 I serve as 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.

 

some addictions

Photograph of a sign: Tourists are not permitted beyond this point

Literature

What is Jazz?

Running

Photography