Learning by Reading and Learning to Read

AAAI 2009 Spring Symposium

March 23 - 25, 2009

Stanford University

The majority of human knowledge is encoded in text, and much of this text is available in machine readable form on the web. But to machines, the knowledge encoded in the texts they read remains inaccessible. Significant progress has been made in such basic areas of language processing as morphological analysis, syntactic parsing, proper name recognition, and logical form extraction. This has already advanced information extraction and filtering capabilities, as a variety of current application systems demonstrate. Still, intelligent machines of today cannot yet claim to be able to generate semantic representations on the scale and of the depth sufficient to support automatic reasoning, a situation often blamed on the knowledge acquisition bottleneck.

The goal of this symposium is to stimulate discussion and open exchange of ideas about two aspects of making texts semantically accessible to and processable by machines. The first, learning by reading, relates to automatically extracting machine-understandable (machine-tractable) knowledge from text. The second, learning to read, is related to automating the process of knowledge extraction required to acquire and expand resources (e.g., ontologies and lexicons) that facilitate learning by reading. There is a clear symbiotic relationship between these to aspects - expanding knowledge resources enables systems that extract knowledge from text to improve at that task over time and vice versa. Given significant diversity in topics, terminology, and writing styles, learning to read will be crucial to large-scale deployment of systems that learn by reading.

Topics of interest include, but are not limited to, the following:

• Extracting ontologies de novo from text
• Expanding ontologies (learning new concepts or properties) by automatic processing of text
• Expanding lexicons (adding new terms or linking lexicons to ontologies) through automatic text processing
• End-to-end self-bootstrapping systems that learn by reading by learning to read
• Special challenges posed by extracting knowledge from text gathered from the web
• Semantic integration and interoperability
• Evaluation metrics for systems that learn by reading or learn to read
• Learning from expository texts (e.g., encyclopedias)
• Targeted (goal-directed) machine reading
• Special challenges posed by learning (either to read or by reading) for long periods of time (called "lifelong learning" in the machine learning community)
• Reasoning with knowledge acquired from text
• Knowledge mining

Submission Information: Submissions can be either position statements (no more than 2 pages) or full papers (no more than 8 pages) in standard AAAI format, and should be mailed to either of the co-chairs (sergei@umbc.edu or oates@umbc.edu). PDF format is preferred, both others, such as Word, are acceptable.

Organizing Committee:

• James Allen, University of Rochester
• Peter Clark, Boeing Corporation
• Jon Curtis, Cycorp
• Graeme Hirst, University of Toronto
• Sergei Nirenburg, co-chair, University of Maryland, Baltimore County
• Tim Oates, co-chair, University of Maryland, Baltimore County
• Lenhart Schubert, University of Rochester
• John F. Sowa, VivoMind Inc.

Accepted Papers:

• Toward Never Ending Language Learning Justin Betteridge, Andrew Carlson, Sue Ann Hong, Estevam R. Hruschka Jr., Edith L. M. Law, Tom M. Mitchell, and Sophie H.Wang

• Learning by Reading: Normalizing complex linguistic structures onto a knowledge representation Daniel G. Bobrow, Cleo Condoravdi, Lauri Karttunen, Annie Zaenen

• Learning a Named Entity Tagger from Gazetteers with the Partial Perceptron Andrew Carlson, Scott Gaffney, and Flavian Vasile

• A Study of Machine Reading from Multiple Texts Peter Clark and John Thompson

• Methods of Rule Acquisition in the TextLearner System Jon Curtis, David Baxter, Peter Wagner, John Cabral, Dave Schneider, Michael Witbrock

• Using Wikitology for Cross-Document Entity Coreference Resolution Tim Finin, Zareen Syed, James Mayfield, Paul McNamee, and Christine Piatko

• Steps Towards a 2nd Generation Learning by Reading System Kenneth D. Forbus, Kate Lockwood, Abhishek Sharma, and Emmett Tomai

• Kleo: A Bootstrapping Learning-by-Reading System Doo Soon Kim and Bruce Porter

• Learning and Evaluating the Content and Structure of a Term Taxonomy Zornitsa Kozareva, Eduard Hovy, and Ellen Riloff

• Resolving References and Identifying Existing Knowledge in a Memory Based Parser Kevin Livingston and Christopher K. Riesbeck

• Cross-Document Coreference Resolution: A Key Technology for Learning by Reading James Mayfield, David Alexander, Bonnie Dorr, Jason Eisner, Tamer Elsayed, Tim Finin, Clay Fink, Marjorie Freedman, Nikesh Garera, Paul McNamee, Saif Mohammad, Douglas Oard, Christine Piatko, Asad Sayeed, Zareen Syed, Ralph Weischedel, Tan Xu, and David Yarowsky

• Lexical Inference and the Problem of the Long Tail David D. McDonald

• Discovering Causal and Temporal Relations in Biomedical Texts Rutu Mulkar-Mehta, Jerry R. Hobbs, Chun-Chi Liu, and Xianghong Jasmine Zhou

• Leveraging Lexical Resources for the Detection of Event Relations Martha Palmer, Jena D. Hwang, Susan Windisch Brown, Karin Kipper Schuler, and Arrick Lanfranchi

• What Is This, Anyway: Automatic Hypernym Discovery Alan Ritter, Stephen Soderland, and Oren Etzioni

• Language Understanding as Recognition and Transduction of Numerous Overlaid Patterns Lenhart Schubert