Integrating natural language, knowledge representation and reasoning, and analogical processing to learn by reading

Kenneth D Forbus*, Christopher K Riesbeck, Lawrence A Birnbaum, Kevin Livingston, Abhishek Sharma, Leo Ureel

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

29 Scopus citations

Abstract

Learning by reading requires integrating several strands of AI research. We describe a prototype system, Learning Reader, which combines natural language processing, a large-scale knowledge base, and analogical processing to learn by reading simplified language texts. We outline the architecture of Learning Reader and some of system-level results, then explain how these results arise from the components. Specifically, we describe the design, implementation, and performance characteristics of a natural language understanding model (DMAP) that is tightly coupled to a knowledge base three orders of magnitude larger than previous attempts. We show that knowing the kinds of questions being asked and what might be learned can help provide more relevant, efficient reasoning. Finally, we show that analogical processing provides a means of generating useful new questions and conjectures when the system ruminates off-line about what it has read.

Original languageEnglish (US)
Title of host publicationAAAI-07/IAAI-07 Proceedings
Subtitle of host publication22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference
Pages1542-1547
Number of pages6
StatePublished - 2007
EventAAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference - Vancouver, BC, Canada
Duration: Jul 22 2007Jul 26 2007

Publication series

NameProceedings of the National Conference on Artificial Intelligence
Volume2

Other

OtherAAAI-07/IAAI-07 Proceedings: 22nd AAAI Conference on Artificial Intelligence and the 19th Innovative Applications of Artificial Intelligence Conference
Country/TerritoryCanada
CityVancouver, BC
Period7/22/077/26/07

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Integrating natural language, knowledge representation and reasoning, and analogical processing to learn by reading'. Together they form a unique fingerprint.

Cite this