The TextLearner System: Reading Learning Comprehension

Abstract

The public reporting burden for this collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing the burden, SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS(ES) 10. SPONSOR/MONITOR'S ACRONYM(S)Defense Advanced Approved for public release; distribution is unlimited. SUPPLEMENTARY NOTES ABSTRACTThe goal of DARPA's Reading Learning Comprehension seedling was to determine the feasibility of autonomous knowledge acquisition through the analysis of text. This report describes the results of that effort by detailing the capabilities of the TextLearner prototype, a knowledge-acquisition program that represents the culmination of the year-long effort. Built atop the Cyc Knowledge Base and implemented almost entirely in the formal representation language of CycL, TextLearner is an anomaly in the way of Natural Language Understanding programs. The system operates by generating a an information-rich model of its target document, and uses that model to explore learning opportunities. TextLearner uses this model to generate and evaluate hypotheses, not only about the possible contents of the target document, but about how to interpret unfamiliar natural language constructions it encounters. Thus TextLearner is able to do two important types of learning-content extraction and rule acquisition-that establish, the authors would argue, the value of knowledge acquisition from text as a rich and promising area of reasoning-based Al research. SUBJECT AbstractThe goal of DARPA's Reading Learning Comprehension seedling was to determine the feasibility of autonomous knowledge acquisition through the analysis of text. This report describes the results of that effort by detailing the capabilities of the TextLearner prototype, a knowledge-acquisition program that represents the culmination of the yearlong effort. Built atop the Cyc Knowledge Base and implemented almost entirely in the formal representation language of CycL, TextLearner is an anomaly in the way of Natural Language Understanding programs. The system operates by generating a an informationrich model of its target document, and uses that model to explore learning opportunities. TextLearner uses this model to generate and evaluate hypotheses, not only about the possible contents of the target document, but about how to interpret unfamiliar natural language constructions it encounters. Thus TextLearner is able to do two important types of learning-content extraction and rule acquisition-that establish, the authors would argue, the value of knowledge acquisition from text as a rich and promising area of reasoning-based Al research.-1-

Harnessing Cyc to Answer Clinical Researchers' Ad Hoc Queries

“…In the longer term, the prospects for increasingly automated knowledge acquisition seem bright. We have been working on automated rule learning over large conceptual and relational vocabularies (Cabral et al 2005, Curtis et al 2009), and are participating in the DARPA Machine Reading Program, in support of this goal.…”

“…In the short term, in work with Elizabeth Coppock, we are exploring applying semantic combination rules, in which the co-occurrence of specific patterns of logical interpretation in parts of an input query triggers the production of a correct (possibly different) representation of an overall situation, and the rejection of alternatives. In the longer term, we are exploring techniques for automatically learning logical interpretations of constructions, by reading (Curtis et al 2009) Failing Soft: Semantic Search Based on Cyc. The aforementioned process does not always succeed,…”