Raphael Hoffmann

firstName DOT lastName AT gmail DOT com

My interests are in the intersections of natural language processing, machine learning, and human-computer interaction.

You can find more information on my CV here, or my LinkedIn profile here.

Publications

• Extreme Extraction: Only One Hour per Relation. Paper Raphael Hoffmann, Luke Zettlemoyer, Daniel S. Weld. CoRR abs/1506.06418, 2015.

• Filling Knowledge Base Gaps for Distant Supervision of Relation Extraction. Paper Wei Xu, Raphael Hoffmann, Le Zhao, Ralph Grishman. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2013. Acceptance rate: 26%.

• Interactive Learning of Relation Extractors with Weak Supervision. Dissertation Raphael Hoffmann. University of Washington, 2012.

• Ontological Smoothing for Relation Extraction with Minimal Supervision. Paper Congle Zhang, Raphael Hoffmann, Daniel S. Weld. In Proceedings of the 26th AAAI Conference on Artificial Intelligence (AAAI), 2012. Acceptance rate: 26%.

• Knowledge-Based Weak Supervision for Information Extraction of Overlapping Relations. Paper Slides Source Code Raphael Hoffmann, Congle Zhang, Xiao Ling, Luke Zettlemoyer, Daniel S. Weld. In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2011. Acceptance rate: 26%.

• Learning 5000 Relational Extractors. Paper Slides Raphael Hoffmann, Congle Zhang, Daniel S. Weld.
  In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2010. Acceptance rate: 25%.

• Semi-Supervised Learning of Semantic Classes for Query Understanding -- from the Web and for the Web. Paper Ye-Yi Wang, Raphael Hoffmann, Xiao Li, Jakub Syzmanski. In Proceedings of the ACM Conference on Information and Knowledge Management (CIKM), 2009. Acceptance rate: 15%.

• Using Wikipedia to Bootstrap Open Information Extraction. Paper Daniel S. Weld, Raphael Hoffmann, Fei Wu. In ACM SIGMOD Record 2009

• Amplifying Community Content Creation Using Mixed-Initiative Information Extraction. Paper Slides Madness Raphael Hoffmann, Saleema Amershi, Kayur Patel, Fei Wu, James Fogarty, Daniel S. Weld. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI), 2009. Acceptance rate: 25%. Nomination for best-paper award

• Information Extraction from Wikipedia: Moving Down the Long Tail. Paper Fei Wu, Raphael Hoffmann, Daniel S. Weld. In Proceedings of the ACM International Conference on Knowledge Discovery and Data Mining (KDD), 2008. Acceptance rate: 19%.

• Intelligence in Wikipedia. Paper Daniel S. Weld, Fei Wu, Eytan Adar, Saleema Amershi, James Fogarty, Raphael Hoffmann, Kayur Patel, Michael Skinner. In 23rd AAAI Conference, Chicago, USA 2008.

• Evaluating Visual Cues for Switching Windows on Large Screens. Paper Slides Madness Raphael Hoffmann, Patrick Baudisch, Daniel S. Weld. In Proceedings of the ACM Conference on Human Factors in Computing Systems (CHI), 2008. Acceptance rate: 22%.

• Assieme: Finding and Leveraging Implicit References in a Web Search Interface for Programmers. Paper Slides Raphael Hoffmann, James Fogarty, Daniel S. Weld. In Proceedings of the ACM Symposium on User Interface Software and Technology (UIST), 2007. Acceptance rate: 19%. Highest rated paper

• Fast and Robust Interface Generation for Ubiquitous Applications. Paper Krzysztof Gajos, David B. Christianson, Raphael Hoffmann, Tal Shaked, Kiera Henning, Jing Jing Long, and Daniel S. Weld. In Proceedings of the Seventh International Conference on Ubiquitous Computing (UbiComp), 2005. Acceptance rate: 9%.

• Tool Supported Development of Energy-aware Real-time Applications for Embedded Systems. Paper Markus Ramsauer, Michael Coduro, and Raphael Hoffmann. In Proceedings of the 16th Euromicro Conference on Real-Time Systems (ECRTS), 2004.

Workshop Papers, Demos

• Supporting rule-based representations with corpus-derived lexical information. Paper Annie Zaenen, Cleo Condoravdi, Daniel G. Bobrow, Raphael Hoffmann.
  In NAACL/HLT Workshop on Formalisms and Methodology for Learning by Reading, 2010.
  
  

• Amplifying Community Content Creation Using Mixed-Initiative Information Extraction (Demo). Demo Paper Raphael Hoffmann, Saleema Amershi, Kayur Patel, Fei Wu, James Fogarty, Daniel S. Weld. In Proceedings of the ACM Symposium on User Interface Software and Technology (UIST), 2008.

• Augmenting Wikipedia-Extraction with Results from the Web. Paper Fei Wu, Raphael Hoffmann, Daniel S. Weld. In the "Wikipedia and Artificial Intelligence: An Evolving Synergy" Workshop at 23rd AAAI Conference, 2008.

• End-user Programming at the University of Washington. Paper Daniel S. Weld, Pedro Domingos, Raphael Hoffmann, and Sumit Sanghai. In CHI-06 Workshop on End-User Software Engineering, 2006

• Improving User Interface Personalization. Paper Krzysztof Gajos, Raphael Hoffmann, and Daniel S. Weld. In Proceedings of UIST-04, 2004

Software

• MultiR --- our system for relation extraction using knowledge-based weak supervision

Other stuff

I co-created web-based learning systems Antolin, Onilo, and Owlfinch. With more than 4M users, Antolin is the most popular system of its kind in Europe.