- author = "Tony C. Smith and Ian H. Witten",
- title = "A Genetic Algorithm for the Induction of Natural Language Grammars",
- booktitle = "Proc IJCAI-95 Workshop on New Approaches to Learning for Natural Language Processing",
- year = "1995",
- editor = "Stefan Wermter",
- pages = "17--24",
- address = "Montreal, Canada",
- month = aug # " 21",
- organisation = "AAAI",
- keywords = "genetic algorithms, genetic programming, grammar induction, statistical methods, context-free grammars",
-
URL = "
http://www.cs.waikato.ac.nz/~ml/publications/1995/Smith95-IJCAI.ps.gz",
-
URL = "
http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.51.4685",
- size = "9 pages",
-
abstract = "Strict pattern-based methods of grammar induction are
often frustrated by the apparently inexhaustible
variety of novel word combinations in large corpora.
Statistical methods offer a possible solution by
allowing frequent well-formed expressions to overwhelm
the infrequent ungrammatical ones. They also have the
desirable property of being able to construct robust
grammars from positive instances alone. Unfortunately,
the zero-frequency problem entails assigning a small
probability to all possible word patterns, thus
ungrammatical n-grams become as probable as unseen
grammatical ones. Further, such grammars are unable to
take advantage of inherent lexical properties that
should allow infrequent words to inherit the syntactic
properties of the class to which they belong.
This paper describes a genetic algorithm (GA) that adapts a population of hypothesis grammars towards a more effective model of language structure. The GA is statistically sensitive in that the utility of frequent pat...",
-
notes = "Jan 2020
https://www.aaai.org/Conferences/IAAI/1995/iaai95-brochure.pdf
IJCAI-95 14th International Joint Conference on
Artificial Intelligence workshop W26
Tree genome. Two parent-two child subtree crossover.
Also known as \cite{Smith95agenetic}
Cited by \cite{Araujo:GPEM20}",
