People

I am currently Substitute Professor/Acting Professor for "Language Technology" at the  University of Duisburg-Essen.

• LOEWE Research Group leader - "Text as a process - Linguistic properties of collaboratively constructed Web 2.0 text".
• Senior Researcher - Intelligent Language Systems research group
• Coordinator - Wikulu project.
• Associated Researcher at the  German Institute for International Educational Research
• From Januar to September 2012, I was Substitute Professor/Acting Professor for "Knowledge Mining & Assessment" at the  German Institute for International Educational Research
• In March/April 2012, I was visiting researcher at Bar-Ilan University, Ramat Gan, Israel

 My research interests are:

• Digital Humanities
• Educational NLP
• Enhancing user interaction with NLP
• Large-scale lexical semantics
•  Semantic Relatedness
• Wiki-Mining

Journal Special Issues

• Guest editor for the special issue on "Collaboratively Constructed Language Resources" in the Language Resources and Evaluation Journal.

Organization

• Program co-chair of the upcoming  annual meeting of the German Society for Computational Linguistics and Language Technology (Gesellschaft für Sprachtechnologie & Computerlinguistik – GSCL)  2013
• COLING 2010 - 2nd Workshop on The people's web meets NLP: Collaboratively Constructed Semantic Resources
• ACL/IJCNLP 2009 - The people's web meets NLP: Collaboratively Constructed Semantic Resources
• Co-organizer of the  SemEval 2013 task on phrasal semantics

Scientific Advisory Board

• I am a member of the Scientific Advisory Board of the EU project  “EXploring Customer Interactions through Textual EntailMENT (EXCITEMENT)”

Memberships

• I am a member of the DFG Network „Empirische Erforschung internetbasierter Kommunikation (Empirical Research on Computer-mediated Communication)“
• I am a member of  ACL,  GI, and  GSCL.

Program Committee / Reviewer

• Books
  • Springer edited Volume “The People’s Web Meets NLP: Collaboratively Constructed Language Resources”
• Journals
  • ACM Transactions on Speech and Language Processing
  • AI Journal, Special Issue "Wiki AI"
  • IEEE-Transaction on Knowledge and Data Engineering (IEEE-TKDE)
  • Journal on Data Semantics (JODS)
  • Journal for Language Technology and Computational Linguistics
  • Language Resources and Evaluation Journal
  • Natural Language Engineering Journal
• Conferences
  • ACL, AAAI, COLING, EACL, EMNLP, ICSC, KONVENS, LREC, NAACL, WWW

• Minerva Short Term Research Grant, 2012
• Winning Team – Semantic Text Similarity Challenge at SemEval 2012. Best result among 35 international teams.
• “Helping Our Own” Challenge 2011. Best detection scores for 8 out of 13 error classes (among 6 participating systems)
• Invitation to the 4th Indo-German Frontiers of Engineering Symposium by the Alexander von Humboldt Foundation, 2012
• IBM PhD Fellowship Award, 2009
• EMNLP Best Reviewer Award, 2009

• Co-Editor of the Special issue on "Collaboratively Constructed Language Resources" in the Language Resources and Evaluation Journal. Available online. To be printed in fall 2012.
• Torsten Zesch and Iryna Gurevych. Wisdom of Crowds versus Wisdom of Linguists - Measuring the Semantic Relatedness of Words. In: Journal of Natural Language Engineering., vol. 16, no. 01, p. 25-59, 2010.
• Torsten Zesch. Measuring Contextual Fitness Using Error Contexts Extracted from the Wikipedia Revision History. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2012), p. 529-538, April 2012.
  Acceptance rate: 27%
• Torsten Zesch, Christof Müller, and Iryna Gurevych. Using Wiktionary for Computing Semantic Relatedness. In: Proceedings of the 23rd AAAI Conference on Artificial Intelligence, p. 861-867, Juli 2008.
  Acceptance rate: 24%, Google Scholar cites: >50
• Torsten Zesch, Christof Müller, and Iryna Gurevych. Extracting Lexical Semantic Knowledge from Wikipedia and Wiktionary. In: Proceedings of the 6th International Conference on Language Resources and Evaluation, Mai 2008.
  Google Scholar cites: >150

A full list of my publications can be found at the bottom of this page or on  Google Scholar.

I actively participate in the development of several software projects (mostly open source):

• JWPL - Wikipedia Application Programming Interface
• DKPro - Repository of flexible NLP components based on Apache UIMA
• jWeb1T - Java Web1T format API
• Wikulu - Self-organizing Wikis

The current state of software development contributions is documented on: http://www.ohloh.net/accounts/TorstenZesch

• I hold a Dr.-Ing. degree from Technische Universität Darmstadt.
• I hold a Diploma in computer science from the Chemnitz University of Technology, Germany.

• Third Symposium of the DFG Network on “Empirische Erforschung internetbasierter Kommunikation”, February 2012, Berlin, Germany – „Multi-level annotation in linguistic preprocessing”
• Colloquium at Bar-Ilan University, March 2012, Ramat Gan, Israel, “Natural Language Processing with UIMA”
• Colloquium at Bar-Ilan University, April 2012, Ramat Gan, Israel, “Semantic Text Similarity for Automatic Free Text Assessment”
• Webkorpora in Computerlinguistik und Sprachforschung, September 2012, IDS Mannheim, Germany, „Gewinnung, Aufbereitung und Analyse von Korpora zu Genres internetbasierter Kommunikation“
• Second Symposium of the DFG Network on “Empirische Erforschung internetbasierter Kommunikation”, October 2011, Münster, Germany – „Annotation of discourse structure in Wikipedia discussions”
• First Symposium of the DFG Network on “Empirische Erforschung internetbasierter Kommunikation”, February 2011, Dortmund, Germany – „Natural Language Processing and the Web“
• DFG Round Table Session "Web Research”, May 2011, Darmstadt – “Semi-automatically semantifying the Web”
• FLaReNet Forum, February 2010, Barcelona, Spain – "What's the difference? Comparing Expert-built and Collaboratively-built Semantic Resources"
• DAI Labor Berlin, July 2010 – “Wisdom of Crowds vs. Wisdom of Linguists - Computing Semantic Relatedness Using Collaboratively Constructed Semantic Resources"
• Cognition Langues Langage Ergonomie (CLLE), Université de Toulouse-Le Mirail, Toulouse, France, September 2010 – “Introduction to the collaboratively constructed semantic resources Wikipedia and Wiktionary”
• First "Web Research" Symposium of the Web Research Center Darmstadt, Darmstadt, Germany, November 2010 – „Knowledge technology for automatic understanding of Web texts”
• Knowledge Media Institute (KMi), Milton Keynes, UK, Dezember 2010 – “Wisdom of Crowds vs. Wisdom of Linguists - Computing Semantic Relatedness Using Collaboratively Constructed Semantic Resources"
• Organisations, Information and Knowledge (OAK) Group, Sheffield University, Dezember 2010 – “Semantic Relatedness Measures – New developments and limits”
• Safety & Security Systems in Europe: IT for Security - Security for IT, "Semantic Language Processing for Security", 9th - 10th October, 2007, Potsdam, Germany

• WS 12/13 - Lecture “Foundations of Language Technology / Grundlagen Intelligenter Systeme”, Technische Universität Darmstadt (with Prof. Dr. Iryna Gurevych)
• SS 12 - Lecture "Lexical-Semantic Methods for Language Understanding", Technische Universität Darmstadt (with Prof. Dr. Iryna Gurevych)
• SS 12 - Project class "Managing Unstructured Information” with a focus on educational applications, Technische Universität Darmstadt
• WS 11/12 - Lecture "Foundations of Language Technology / Grundlagen Intelligenter Systeme", Technische Universität Darmstadt
• WS 11/12 - Lecture "Natural Language Processing and the Web" (with Jun-Prof. Dr. Chris Biemann), Technische Universität Darmstadt
• SS 11 - Lecture "Educational Natural Language Processing" (with Prof. Dr. Iryna Gurevych), Technische Universität Darmstadt
• WS 10/11 - Tutorial "Foundations of Language Technology" (with Ute Blechschmidt-Trapp and Steve Maslennikov), Technische Universität Darmstadt
• SS 10 - Lecture "Lexical-Semantic Methods for Language Understanding" (with Prof. Dr. Iryna Gurevych), Technische Universität Darmstadt
• SS 09 - Seminar on "Knowledge Management in Web 2.0" (with Prof. Dr. Iryna Gurevych and Johannes Hoffart), Technische Universität Darmstadt
• WS 08/09 - Tutorial on "Natural Langauge Processing and the Web" (with Christof Müller and Niklas Jakob), Technische Universität Darmstadt
• WS 06/07 - Seminar on Unstructured Information Management at the University of Tübingen (with Prof. Dr. Iryna Gurevych and Christof Müller)

I co-supervise(d) the following theses

• Niklas Jakob -- Developing a generic interface for semantic networks
• Christian Jacobi -- Using Wikipedia in Information Retrieval: a case study on "Electronic Career Guidance"
• Cigdem Toprak -- Sentiment detection in natural language texts based on a case study: Analysis of professional features
• Lars Lipecki -- Experimental analysis of semantic relatedness
• Florian Schwager -- Automatic analysis of lexical cohesion
• Marius Lauder -- Extracting domain-specific thesauri from Wikipedia and Wiktionary
• Lizhen Qu -- Using Semantic Knowledge to Improve Information Search in Web 2.0
• Simon Kulessa -- Extracting paraphrases from the Wikipedia revision history
• Mateusz Parzonka - Using Text Segmentation to Improve Back-Of-The-Book Indexing
• Marko Martin -- Applying Graph Algorithms to Text Segmentation (nominated for GSCL Student Thesis Award)
• Irina Smidt -- Mining Error Contexts from the Wikipedia Revision History for Correcting Grammar Errors
• Svenja Stark -- Correcting Article and Preposition Errors in German Documents
• Georgi Valkanov -- Generating Entity-Sets for Odd-one-out Questions