Curriculum Vitae

• I am currently a visiting researcher at UC Berkeley working as a post-doc in the AI/FrameNet group at the International Computer Science Institute (ICSI).
  
  
• Previously, I was a member of the Databases and Information Systems Group headed by Gerhard Weikum at the Max Planck Institute for Informatics, receiving my doctoral degree from Saarland University, Saarbrücken, Germany in 2010.
  
  
• In 2011, I spent 4 amazing months at the Machine Learning and Perception Group (headed by Christopher Bishop) at Microsoft Research Cambridge, working with Thore Graepel and Gjergji Kasneci.

Current Research Foci

The vision driving my research is the idea that there is now so much digital data out there that machines should be able to better make sense of human language, make sense of the world, and hence better serve our needs. By smartly drawing on various sorts of knowledge available on the Web as well as statistical learning methods, we can produce systems that improve our daily life, e.g. through better web search, data organization, and multilingual support. More specifically, my research interests include:

• Web and Text Mining, especially to produce large-scale repositories of semantic knowledge about entities and their relationships
• Integrating and ranking information from heterogeneous data sources
• Applications of Machine Learning, Graph Algorithms to Web, Natural Language Processing, and Data Integration Problems
• Multilingual and cross-lingual natural language processing

Awards and Recognition

• Best Demonstration Award (with Johannes Hoffart, Fabian Suchanek, Klaus Berberich, Edwin Lewis-Kelham, Gerhard Weikum)
  20th International World Wide Web Conference (WWW 2011)
  
  
• Best Interdisciplinary Paper Award (out of 945 full paper submissions)
  19th ACM Conference on Information and Knowledge Management (CIKM 2010)
  
  
• Best Paper Award
  International Conference on Global Interoperability for Language Resources (ICGL 2008)
  
  
• Nominee for Best German/Swiss/Austrian Computer Science Dissertation 2010 (GI-Dissertationspreis 2010)
  
  
• Doctoral Scholarship: 2007-2010
  IMPRS-CS
  
  
• Foreign Studies Scholarship: 2004-2005, Université de Montréal, Canada
  German National Academic Foundation / Studienstiftung des deutschen Volkes
  
  
• Scholarship: 2003-2006
  German National Academic Foundation / Studienstiftung des deutschen Volkes
  
  
• Online-Scholarship (alumnus)
  e-fellows.net
  
  

Resources

• UWN/MENTA: A large-scale multilingual lexical knowledge base built using statistical methods, transforming the well-known WordNet database into a massively multilingual resource covering over 1 million words and several million named entities in a single large multilingual taxonomy.
  
  
• Lexvo.org: Contributes information about words and other language-related entities to the Linked Data Web and Semantic Web, leading to a Web of Data in which the British Library, the Spanish National Library, and others have linked their data to Lexvo.org, and Lexvo.org in turn connects its own data to other valuable resources.
  
  
• YAGO-SUMO Integration: An ontology providing an enormous body of axiomatized world knowledge based on YAGO as well as the Suggested Upper Merged Ontology (SUMO).
  
  
• SPASS-XDB: Online interface to the SPASS-XDB reasoning system, which combines state-of-the-art theorem proving with support for large-scale knowledge sources
  
  
• MTRogets: Thesauri in many languages, obtained by translating Roget's Thesaurus using task-specific statistical techniques
  
  
• Etymological Wordnet: A database of etymological and derivational relationships between words in different languages, mined from Wiktionary.
  
  
• Online Transliteration Service: A service that for instance will transliterate the Greek "ψυχολογία" into "psychología".
  
  
• Wikipedia IMDb Mappings: Mappings between Wikipedia articles and corresponding Internet Movie Database entries (Download)

Publications

• Taxonomic Data Integration from Multilingual Wikipedia Editions   
  Gerard de Melo, Gerhard Weikum (in submission)
  In: Knowledge and Information Systems, Springer.
  
  
• UWN: A Large Multilingual Lexical Knowledge Base (Demonstration Paper)   
  Gerard de Melo, Gerhard Weikum (2012)
  In: Proc. ACL 2012.
  
  
• Empirical Comparisons of MASC Word Sense Annotations   PDF    BibTeX   Blog
  Gerard de Melo, Collin F. Baker, Nancy Ide, Rebecca Passonneau, Christiane Fellbaum (2012)
  In: Proc. LREC 2012. ELRA.
  
  
• Precedes: A Semantic Relation in FrameNet   PDF    BibTeX
  Miriam R.L. Petruck, Gerard de Melo (2012)
  In: Proc. LREC 2012 Workshop on Language Resources for Public Security Applications.
  
  
• Constructing and Utilizing Wordnets using Statistical Methods   BibTeX
  Gerard de Melo, Gerhard Weikum (2012)
  Journal Language Resources and Evaluation, Springer Verlag, Dordrecht, Netherlands.
  
  
• Graph-based Methods for Large-Scale Multilingual Knowledge Integration  Order online   BibTeX
  Gerard de Melo (2012)
  universaar - Saarland University Press, Saarbrücken, Germany. ISBN 978-3-86223-028-0.
  (Print version of doctoral dissertation)
  
  
• Deriving a Web-Scale Common Sense Fact Database   PDF   BibTeX
  Niket Tandon, Gerard de Melo, Gerhard Weikum (2011)
  In: Proc. AAAI 2011. San Francisco, CA, USA.
  
  
• Graphenbasierte Methoden zur multilingualen Wissensintegration   BibTeX
  Gerard de Melo (2011)
  In: Ausgezeichnete Informatikdissertationen 2010, Gesellschaft für Informatik LNI D-11.
  
  
• An Application: Extending SUMO with Wikipedia (Book Chapter)
  Gerard de Melo, Fabian Suchanek, Adam Pease (2011)
  In: Adam Pease. Ontology: A Practical Guide. Articulate Software, USA. ISBN: 1-889455-10-5.
  
  
• YAGO2: Exploring and Querying World Knowledge in Time, Space, Context, and Many Languages (Demo Paper)   PDF    BibTeX
  Johannes Hoffart, Fabian Suchanek, Klaus Berberich, Edwin Lewis-Kelham, Gerard de Melo, Gerhard Weikum (2011)
  In: Proc. 20th International World Wide Web Conference (WWW 2011)
  **Best Demonstration Award**
  
  
• Graph-based Methods for Large-Scale Multilingual Knowledge Integration   PDF    BibTeX
  Gerard de Melo (2010)
  Doctoral Dissertation. Saarland University, Saarbrücken, Germany.
  Committee: Gert Smolka, Gerhard Weikum, Hans Uszkoreit, Hinrich Schütze
  Grade: summa cum laude
  
  
• MENTA: Inducing Multilingual Taxonomies from Wikipedia   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2010)
  In: Proc. 19th ACM Conference on Information and Knowledge Management (CIKM 2010), Toronto, Canada. ACM, New York, USA.
  Acceptance rate: 13.3%.
  **Best Interdisciplinary Paper Award** (out of 945 full paper submissions)
  
  
• Information Extraction from Web-Scale N-Gram Data   PDF    BibTeX
  Niket Tandon, Gerard de Melo (2010)
  In: Proc. Web N-gram Workshop at SIGIR 2010.
  
  
• Untangling the Cross-Lingual Link Structure of Wikipedia   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2010)
  In: Proc. 48th Annual Meeting of the Association for Computational Linguistics (ACL 2010), Uppsala, Sweden.
  
  
• Providing Multilingual, Multimodal Answers to Lexical Database Queries   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2010)
  In: Proc. 7th Language Resources and Evaluation Conference (LREC 2010), ELRA, Paris, France.
  
  
• Progress Towards Effective Automated Reasoning with World Knowledge   PDF    BibTeX
  Geoff Sutcliffe, Martin Suda, Alexandra Teyssandier, Nelson Dellis, Gerard de Melo (2010)
  In: Proc. 23rd International FLAIRS Conference, AAAI Press, Menlo Park, CA, USA.
  
  
• Towards Universal Multilingual Knowledge Bases   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2010)
  In: Principles, Construction, and Applications of Multilingual Wordnets. Proc. 5th Global Wordnet Conference (GWC 2010), Narosa Publishing, New Delhi, India.
  
  
• Towards a Universal Wordnet by Learning from Combined Evidence   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2009)
  In: Proc. 18th ACM Conference on Information and Knowledge Management (CIKM 2009), Hong Kong, China. ACM, New York, USA.
  Acceptance rate: 14.5%.
  
  
• Extracting Sense-Disambiguated Example Sentences From Parallel Corpora   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2009)
  In: Proc. Workshop on Definition Extraction at RANLP 2009, Borovets, Bulgaria.
  
  
• External Sources of Axioms in Automated Theorem Proving   PDF   BibTeX
  Martin Suda, Geoff Sutcliffe, Patrick Wischnewski, Manuel Lamotte-Schubert, Gerard de Melo (2009)
  In: Proc. 32nd Annual Conference on Artificial Intelligence (KI 2009), Springer-Verlag (LNAI 5803), Berlin / Heidelberg, Germany.
  
  
• Integrating YAGO into the Suggested Upper Merged Ontology (Short Paper)   PDF   BibTeX   Technical Report
  Gerard de Melo, Fabian Suchanek, Adam Pease (2008)
  In: Proc. 20th IEEE ICTAI 2008, IEEE Computer Society, Los Alamitos, CA, USA.
  
  
• Language as a Foundation of the Semantic Web (Poster Paper)   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2008)
  In: Proc. Poster And Demonstration Session of the 7th International Semantic Web Conference (ISWC 2008), CEUR Vol. 401, Karlsruhe, Germany.
  
  
• Mapping Roget's Thesaurus and WordNet to French   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2008)
  In: Proc. 6th Language Resources and Evaluation Conference (LREC 2008), ELRA, Paris, France.
  
  
• A Machine Learning Approach to Building Aligned Wordnets   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2008)
  In: Proc. International Conference on Global Interoperability for Language Resources (ICGL 2008), Hong Kong, China.
  **Best Paper Award**
  
  
• On the Utility of Automatically Generated Wordnets   PDF    BibTeX
  Gerard de Melo, Gerhard Weikum (2007)
  In: Proc. Fourth Global WordNet Conference (GWC 2008), Szeged, Hungary.
  
  
• Multilingual Text Classification using Ontologies   PDF    BibTeX
  Gerard de Melo, Stefan Siersdorfer (2007)
  In: Proc. 29th European Conference on Information Retrieval (ECIR 2007), Rome, Italy, Springer-Verlag (LNCS 4425), Berlin / Heidelberg, Germany.
  Acceptance Rate: 27.7%
  
  
• Adaptive Multilingual Text Classification using Ontologies
  Gerard de Melo (2006)
  Diplomarbeit (Master Thesis). Johann Wolfgang Goethe-Universität Frankfurt am Main, Germany.