The structure-mapping engine: algorithm and examples
Artificial Intelligence
Model-based reasoning about learner behaviour
Artificial Intelligence
Dynamic Case Creation and Expansion for Analogical Reasoning
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Partition-based logical reasoning for first-order and propositional theories
Artificial Intelligence - Special volume on reformulation
Unsupervised named-entity extraction from the web: an experimental study
Artificial Intelligence
Extracting product features and opinions from reviews
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Transforming between propositions and features: bridging the gap
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 2
Searching for common sense: populating Cyc™ from the web
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
The Future of Text-Meaning in Computational Linguistics
TSD '08 Proceedings of the 11th international conference on Text, Speech and Dialogue
Knowledge integration across multiple texts
Proceedings of the fifth international conference on Knowledge capture
Analogical dialogue acts: supporting learning by reading analogies
FAM-LbR '10 Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading
Syntactic principles of heuristic-driven theory projection
Cognitive Systems Research
Using natural language to integrate, evaluate, and optimize extracted knowledge bases
Proceedings of the 2013 workshop on Automated knowledge base construction
Hi-index | 0.00 |
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.