A prototype system that learns by reading simplified texts

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

4 Citations (Scopus)

Abstract

Systems that could learn by reading would radically change the economics of building large knowledge bases. This paper describes Learning Reader, a prototype system that extends its knowledge base by reading. Learning Reader consists of three components. The Reader, which converts text into formally represented cases, uses a Direct Memory Access Parser operating over a large knowledge base, derived from ResearchCyc. The Q/A system, which provides a means of quizzing the system on what it has learned, uses focused sets of axioms automatically extracted from the knowledge base for tractability. The Ruminator, which attempts to improve the system's understanding of what it has read by off-line processing, generates questions for itself by several means, including analogies with prior material and automatically constructed generalizations from examples in the KB and its prior reading. We discuss the architecture of the system, how each component works, and some experimental results.

Original languageEnglish (US)
Title of host publicationMachine Reading - Papers from the 2007 AAAI Spring Symposium, Technical Report
Pages49-54
Number of pages6
VolumeSS-07-06
StatePublished - Dec 28 2007
Event2007 AAAI Spring Symposium - Stanford, CA, United States
Duration: Mar 26 2007Mar 28 2007

Other

Other2007 AAAI Spring Symposium
CountryUnited States
CityStanford, CA
Period3/26/073/28/07

Fingerprint

Data storage equipment
Economics
Processing

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Forbus, K. D., Riesbeck, C. K., Birnbaum, L. A., Livingston, K., Sharma, A., & Ureel, L. (2007). A prototype system that learns by reading simplified texts. In Machine Reading - Papers from the 2007 AAAI Spring Symposium, Technical Report (Vol. SS-07-06, pp. 49-54)
Forbus, Kenneth D ; Riesbeck, Christopher K ; Birnbaum, Lawrence A ; Livingston, Kevin ; Sharma, Abhishek ; Ureel, Leo. / A prototype system that learns by reading simplified texts. Machine Reading - Papers from the 2007 AAAI Spring Symposium, Technical Report. Vol. SS-07-06 2007. pp. 49-54
@inproceedings{9fcdfc886cb04353a4ad2c14b1350c80,
title = "A prototype system that learns by reading simplified texts",
abstract = "Systems that could learn by reading would radically change the economics of building large knowledge bases. This paper describes Learning Reader, a prototype system that extends its knowledge base by reading. Learning Reader consists of three components. The Reader, which converts text into formally represented cases, uses a Direct Memory Access Parser operating over a large knowledge base, derived from ResearchCyc. The Q/A system, which provides a means of quizzing the system on what it has learned, uses focused sets of axioms automatically extracted from the knowledge base for tractability. The Ruminator, which attempts to improve the system's understanding of what it has read by off-line processing, generates questions for itself by several means, including analogies with prior material and automatically constructed generalizations from examples in the KB and its prior reading. We discuss the architecture of the system, how each component works, and some experimental results.",
author = "Forbus, {Kenneth D} and Riesbeck, {Christopher K} and Birnbaum, {Lawrence A} and Kevin Livingston and Abhishek Sharma and Leo Ureel",
year = "2007",
month = "12",
day = "28",
language = "English (US)",
isbn = "9781577353157",
volume = "SS-07-06",
pages = "49--54",
booktitle = "Machine Reading - Papers from the 2007 AAAI Spring Symposium, Technical Report",

}

Forbus, KD, Riesbeck, CK, Birnbaum, LA, Livingston, K, Sharma, A & Ureel, L 2007, A prototype system that learns by reading simplified texts. in Machine Reading - Papers from the 2007 AAAI Spring Symposium, Technical Report. vol. SS-07-06, pp. 49-54, 2007 AAAI Spring Symposium, Stanford, CA, United States, 3/26/07.

A prototype system that learns by reading simplified texts. / Forbus, Kenneth D; Riesbeck, Christopher K; Birnbaum, Lawrence A; Livingston, Kevin; Sharma, Abhishek; Ureel, Leo.

Machine Reading - Papers from the 2007 AAAI Spring Symposium, Technical Report. Vol. SS-07-06 2007. p. 49-54.

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

TY - GEN

T1 - A prototype system that learns by reading simplified texts

AU - Forbus, Kenneth D

AU - Riesbeck, Christopher K

AU - Birnbaum, Lawrence A

AU - Livingston, Kevin

AU - Sharma, Abhishek

AU - Ureel, Leo

PY - 2007/12/28

Y1 - 2007/12/28

N2 - Systems that could learn by reading would radically change the economics of building large knowledge bases. This paper describes Learning Reader, a prototype system that extends its knowledge base by reading. Learning Reader consists of three components. The Reader, which converts text into formally represented cases, uses a Direct Memory Access Parser operating over a large knowledge base, derived from ResearchCyc. The Q/A system, which provides a means of quizzing the system on what it has learned, uses focused sets of axioms automatically extracted from the knowledge base for tractability. The Ruminator, which attempts to improve the system's understanding of what it has read by off-line processing, generates questions for itself by several means, including analogies with prior material and automatically constructed generalizations from examples in the KB and its prior reading. We discuss the architecture of the system, how each component works, and some experimental results.

AB - Systems that could learn by reading would radically change the economics of building large knowledge bases. This paper describes Learning Reader, a prototype system that extends its knowledge base by reading. Learning Reader consists of three components. The Reader, which converts text into formally represented cases, uses a Direct Memory Access Parser operating over a large knowledge base, derived from ResearchCyc. The Q/A system, which provides a means of quizzing the system on what it has learned, uses focused sets of axioms automatically extracted from the knowledge base for tractability. The Ruminator, which attempts to improve the system's understanding of what it has read by off-line processing, generates questions for itself by several means, including analogies with prior material and automatically constructed generalizations from examples in the KB and its prior reading. We discuss the architecture of the system, how each component works, and some experimental results.

UR - http://www.scopus.com/inward/record.url?scp=37349065826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=37349065826&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:37349065826

SN - 9781577353157

VL - SS-07-06

SP - 49

EP - 54

BT - Machine Reading - Papers from the 2007 AAAI Spring Symposium, Technical Report

ER -

Forbus KD, Riesbeck CK, Birnbaum LA, Livingston K, Sharma A, Ureel L. A prototype system that learns by reading simplified texts. In Machine Reading - Papers from the 2007 AAAI Spring Symposium, Technical Report. Vol. SS-07-06. 2007. p. 49-54