- author = "Thomas R. Osborn and Adib Charif and Ricardo Lamas and Eugene Dubossarsky",
- title = "Genetic Logic Programming",
- booktitle = "1995 IEEE Conference on Evolutionary Computation",
- year = "1995",
- volume = "2",
- pages = "728",
- address = "Perth, Australia",
- publisher_address = "Piscataway, NJ, USA",
- month = "29 " # nov # " - 1 " # dec,
- publisher = "IEEE Press",
- keywords = "genetic algorithms, genetic programming, prolog",
-
URL = "
http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/glpfinal.ps.gz",
- size = "5 pages",
-
abstract = "
Genetic Logic Programming (GLP) is a new method which applies the Genetic Algorithms paradigm to Declarative Programming - specifically to evolve populations of Prolog programs. This talk examines GLP applied to Natural Language Understanding to illustrate the power, issues and limitations of GLP. Populations of Prolog query interpreters evolve to respond more correctly to queries about the Aesop fable: {"}The Fox and the Crow{"}. The interpreters process parsed text and consult a general knowledge-base. The gene pool consists of a large set of Prolog rules and facts which are tentatively proposed as being 'useful' for interpretation. Essentially, interpreters act as an interface between queries, knowledge bases and the text. Closure and termination are addressed at the level of design of the gene pool, and various Prolog options.
Fitness amounts to a score on a high school like {"}comprehension test{"}, with special care to deal with redundant and dependent answers, and with an eye to rewarding correct higher-level abstractions.
glpfinal.ps.gz 3 July 2002 Here is the final version of the paper. The corrections are minor but the formating is much better.",
-
notes = "ICEC-95 Editors not given by IEEE, Organisers David
Fogel and Chris deSilva.
conference details at http://ciips.ee.uwa.edu.au/~dorota/icnn95.html
Posting by Tom to GP list Thu, 01 Feb 1996 13:50:40 +1100
The gist was applying evolutionary methods to (Prolog) Logic Programs, which were applied to NLU. There are several subtlties which are covered in the paper - notions of fitness in terms of measured program correctness, the evolving thing was an interface between (parsed) text and lexicons and knowledge-base(s), genes were 'hooks' into the KB (either a rule or several, ...), and termination and closure were tricky.
",
