Category Posts Navigation

Aristo – Answer Questions with a Knowledgeable Machine

Posted by Marcus Zillman

Aristo – Answer Questions with a Knowledgeable Machine
http://allenai.org/aristo.html

Aristo is a system that acquires and stores a vast amount of knowledge in computable form, then applies this knowledge to answer a variety of science questions from standardized exams for students in multiple grade levels. Key elements: a) Natural language parsing and processing of a variety of knowledge sources into a structured, computable knowledge base; b) Question understanding; transforming questions, diagrams, and answer options from exams into computable input; c) Integration with diagram processing systems to go beyond text to successfully understand exam questions; and d) An array of solvers using various statistical and inference techniques to either select or generate the correct answer. Aristo works as follows: 1) Knowledge Extraction – Facts are extracted from various sources and processed into a structured knowledge base; 2) Question Understanding – Questions are parsed and processed along with their accompanying diagrams to best determine a strategy for answering; and 3) Providing Answers – Aristo’s solvers use entailment, statistical analysis, and inference methods to produce the right answer. This will be added to Artificial Intelligence Resources Subject Tracer™. This will be added to Web Data Extractors white paper. This will be added to Internet Expert Resources Subject Tracer™. This will be added to Entrepreneurial Resources Subject Tracer™.

Leave a Reply

Facebook Comments

Sign up for Awareness Watch Newsletter

* = required field

Browse Categories