Machine Reading

This Spring, 590a will be on "Machine Reading" - the process of extracting high-level knowledge from natural language text, for example from Web pages. Most people know about the work on machine reading which is happening here at UW CSE (e.g. KnowItAll, TextRunner, Kylin, and the work based on Markov Logic Networks), but the area is also heating up dramatically at other Universities and research labs. We'll spend the quarter reading the latest papers on the topic and brainstorming about new directions. Participants may be asked to help lead class discussion of papers or to talk about their ongoing research on the topic.

Mailing List

We will not use the cse590a mailing list. Instead, announcements about the seminar will go to uw-ai. If you do not already subscribe to uw-ai, then join by sending mail to uw-ai-request@cs.washington.edu, with the line "subscribe listname" in the body of the message. You are welcome to discuss the presentations on the mailing list.

Calendar

List of papers

• TextRunner
  • Oren Etzioni, Michele Banko, Stephen Soderland, and Daniel S. Weld. Open Information Extraction from the Web. Communications of the ACM, 51(12): 68-74, 2008.
  • Michele Banko, Michael J Cafarella, Stephen Soderland, Matt Broadhead, and Oren Etzioni. Open Information Extraction from the Web. IJCAI 2007.
• Markov Logic Networks
  • Hoifung Poon, Pedro Domingos. Joint Unsupervised Coreference Resolution with Markov Logic, EMNLP 08.
  • Stanley Kok and Pedro Domingos. Extracting Semantic Networks from Text Via Relational Clustering, ECML 08.
• Kylin
  • Fei Wu, Raphael Hoffmann, Daniel S. Weld. Information Extraction from Wikipedia: Moving Down the Long Tail, KDD 08.
• Semantic Parsing
  • Luke S. Zettlemoyer and Michael Collins. Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars, UAI 05. slides
  • Luke S. Zettlemoyer and Michael Collins. Online Learning of Relaxed CCG Grammars for Parsing to Logical Form, EMNLP-CoNLL 2007.
  • Raymond J. Mooney. Learning for Semantic Parsing, Computational Linguistics and Intelligent Text Processing (CICLing), 2007.
  • David L. Chen and Raymond J. Mooney. Learning to Sportscast: A Test of Grounded Language Acquisition, ICML 08.
  • Yuk Wah Wong and Raymond J. Mooney. Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus, ACL 07.
• Mobius
  • Ken Barker et al. Learning by Reading: A protoype System, Performance Baseline and Lessons Learned. AAAI 2007.
  • Doo Soon Kim and Bruce Porter. Kleo: A Bootstrapping Learning-by-Reading System. AAAI Spring Symposium 2009 (Learning by Reading and Learning to Read).
• KNext
  • Benjamin Van Durme and Lenhart K. Schubert. Open knowledge extraction using compositional language processing, Symposium on Semantics in Systems for Text Processing (STEP 2008).
  • Benjamin Van Durme, Ting Qian and Lenhart K. Schubert. "Class-driven attribute extraction". COLING'08.
• Boeing
  • P. Clark, J. Thompson. A Study of Machine Reading from Multiple Texts. To appear in the AAAI Spring Symposium on Learning by Reading and Learning to Read, 2009.
  • Peter Clark and Phil Harrison. Boeing's NLP System and the Challenges of Semantic Representation. STEP 2008.
• CMU Read the Web
  • Justin Betteridge, Andrew Carlson, Sue Ann Hong, Estevam R. Hruschka Jr.,Edith L. M. Law, Tom M. Mitchell and Sophie H.Wang. Toward Never Ending Language Learning. slides AAAI Spring Symposium on Learning by Reading and Learning to Read, 2009.
  • Andrew Carlson, Justin Betteridge, Estevam R. Hruschka Jr. and Tom M. Mitchell. Coupling Semi-Supervised Learning of Categories and Relations. To appear at the NAACL HLT 2009 Workshop on Semi-supervised Learning for Natural Language Processing.
• Other
  • Forbus, K., Riesbeck, C., Birnbaum, L., Livingston, K., Sharma, A., and Ureel, L. Integrating Natural Language, Knowledge Representation and Reasoning, and Analogical Processing to Learn by Reading. AAAI-07.
  • James Mayfield et al. Cross-Document Coreference Resolution: A Key Technology for Learning by Reading. AAAI Spring Symposium, 2009.
  • Rutu Mulkar-Mehta, Jerry Hobbs, Chun-Chi Liu and Xianghong Jasmine Zhou. Discovering Causal and Temporal Relations in Biomedical Texts. To appear, AAAI Spring Symposium '09.
  • Jing Jiang and ChengXiang Zhai. A Systematic Exploration of the Feature Space for Relation Extraction, HLT 07.