Generating Numerical Literals During Refinement

Simon Anthony; Alan M. Frisch; N. Lavrac; S. Dzeroski

Generating Numerical Literals During Refinement

Simon Anthony, Alan M. Frisch, N. Lavrac, S. Dzeroski

Computer Science

Research output: Contribution to conference › Paper

Abstract

Despite the rapid emergence and success of Inductive Logic Programming, problems still surround number handling---problems directly inherited from the choice of logic programs as the representation language. Our conjecture is that a generalisation of the representation language to Constraint Logic Programs provides an effective solution to this problem. We support this claim with the presentation of an algorithm called NUM, to which a top-down refinement operator can delegate the task of finding numerical literals. NUM can handle equations, in-equations and dis-equations in a uniform way, and, furthermore, provides more generality than competing approaches since numerical literals are not required to cover all the positive examples available.

Original language	English
Pages	61-76
Number of pages	16
Publication status	Published - 1997

Access to Document

http://www.cs.york.ac.uk/isg/papers/alan.frisch/num.ps.gz

Cite this

@conference{0b8c554f44814411a8caeba12549f330,

title = "Generating Numerical Literals During Refinement",

abstract = "Despite the rapid emergence and success of Inductive Logic Programming, problems still surround number handling---problems directly inherited from the choice of logic programs as the representation language. Our conjecture is that a generalisation of the representation language to Constraint Logic Programs provides an effective solution to this problem. We support this claim with the presentation of an algorithm called NUM, to which a top-down refinement operator can delegate the task of finding numerical literals. NUM can handle equations, in-equations and dis-equations in a uniform way, and, furthermore, provides more generality than competing approaches since numerical literals are not required to cover all the positive examples available.",

author = "Simon Anthony and Frisch, {Alan M.} and N. Lavrac and S. Dzeroski",

year = "1997",

language = "English",

pages = "61--76",

}

TY - CONF

T1 - Generating Numerical Literals During Refinement

AU - Anthony, Simon

AU - Frisch, Alan M.

AU - Lavrac, N.

AU - Dzeroski, S.

PY - 1997

Y1 - 1997

N2 - Despite the rapid emergence and success of Inductive Logic Programming, problems still surround number handling---problems directly inherited from the choice of logic programs as the representation language. Our conjecture is that a generalisation of the representation language to Constraint Logic Programs provides an effective solution to this problem. We support this claim with the presentation of an algorithm called NUM, to which a top-down refinement operator can delegate the task of finding numerical literals. NUM can handle equations, in-equations and dis-equations in a uniform way, and, furthermore, provides more generality than competing approaches since numerical literals are not required to cover all the positive examples available.

AB - Despite the rapid emergence and success of Inductive Logic Programming, problems still surround number handling---problems directly inherited from the choice of logic programs as the representation language. Our conjecture is that a generalisation of the representation language to Constraint Logic Programs provides an effective solution to this problem. We support this claim with the presentation of an algorithm called NUM, to which a top-down refinement operator can delegate the task of finding numerical literals. NUM can handle equations, in-equations and dis-equations in a uniform way, and, furthermore, provides more generality than competing approaches since numerical literals are not required to cover all the positive examples available.

M3 - Paper

SP - 61

EP - 76

ER -