Stephen Soderland received his bachelor's degree in Mathematics from Stanford University in 1971, a master's degree in Computer Science from the University of Massachusetts in 1995, and a Ph.D. in Computer Science from the University of Massachusetts in 1997. He joined the University of Washington's Department of Computer Science & Engineering as a Research Scientist in May 2003. His primary research interest is natural language processing.

Selected Publications

• Open Language Learning for Information Extraction
  (Experimental Methods in Natural Language Processing (EMNLP), 2012)
• Rel-grams: A Probabilistic Model of Relations in Text
  (Knowledge Base Extraction Workshop at NAACL-HLT (AKBC-WEKEX), 2012)
• Identifying Relations for Open Information Extraction
  (Experimental Methods in Natural Language Processing (EMNLP), 2011)
• Open Information Extraction: the Second Generation
  (International Joint Conference on Artificial Intelligence (IJCAI), 2011)
• Exploiting Hyponymy in Extracting Relations and Enhancing Ontologies
  (IEEE Workshop on Natural Language Processing and Ontology Engineering, 2008)
• It's a Contradiction -- No, It's Not: A Case Study using Functional Relations
  (Empirical Methods in Natural Language Processing (EMNLP), 2008)
• Open Information Extraction from the Web
  (International Joint Conference on Artificial Intelligence (IJCAI), 2007)
• Lexical Translation with Application to Image Search on the Web
  (Machine Translation Summit XI, 2007)
• Building a Sense-Distinguished Multilingual Lexicon from Monolingual Corpora and Bilingual Lexicons
  (Machine Translation Summit XI, 2007)
• Moving from Textual Relations to Ontologized Relations
  (AAAI Spring Symposium on Machine Reading, 2007)
• Cross-lingual Image Search on the Web
  (Workshop on Cross-Lingual Information Access, IJCAI, 2007)
• Ambiguity Reduction for Machine Translation: Human-Computer Collaboration
  (Assoc. for Machine Translation in the Americas (AMTA), 2006)
• A Probabilistic Model of Redundancy in Information Extraction
  (Distinguished Paper Award, IJCAI, 2005)
• Comprehensive Overview of KnowItAll
  (Artificial Intelligence, 2005)
• KnowItNow: Fast, Scalable Information Extraction from the Web
  (Experimental Methods in Natural Language Processing (EMNLP), 2005)
• The Use of Web-based Statistics to Validate Information Extraction
  (Adaptive Text Extraction and Mining (ATEM), 2004)
• Methods for Domain-Independent Information Extraction from the Web: An Experimental Comparison
  (National Conference on Artificial Intelligence (AAAI), 2004)
• Web-Scale Information Extraction in KnowItAll
  (World Wide Web Conference, 2004)
• Building a machine learning based text understanding system
  (Adaptive Text Extraction and Mining (ATEM), 2001)
• Automatic structuring of radiology free-text reports
  (Radiographics, 21, 2001)
• Learning information extraction rules for semi-structured and free text
  (Machine Learning, 34, 233-272, 1999)
• Learning to extract text-based information from the World Wide Web
  (Knowledge Discovery and Data Mining (KDD), 1997)
• Learning Text Analysis Rules for Domain-Specific Natural Language Processing
  (doctoral dissertation at U. Massachusetts, 1997)
• CRYSTAL: Inducing a conceptual dictionary
  (International Joint Conference on Artificial Intelligence (IJCAI), 1995)