DMCA
Natural Language Text Classification and Filtering with Trigrams and Evolutionary Nearest Neighbour Classifiers (2000)
| Citations: | 2 - 0 self |
BibTeX
@MISC{Langdon00naturallanguage,
author = {W. B. Langdon and W. B. Langdon},
title = {Natural Language Text Classification and Filtering with Trigrams and Evolutionary Nearest Neighbour Classifiers},
year = {2000}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
N grams offer fast language independent multi-class text categorization. Text is reduced in a single pass to ngram vectors. These are assigned to one of several classes by a) nearest neighbour (KNN) and b) genetic algorithm operating on weights in a nearest neighbour classifier. 91% accuracy is found on binary classification on short multi-author technical English documents. This falls if more categories are used but 69% is obtained with 8 classes. Zipf law is found not to apply to trigrams. 2000 Mathematics Subject Classification: 68T05, 68T20 1998 ACM Computing Classification System: G.1.6, G.2.1, I.2.6, I.2.8 Keywords and Phrases: genetic algorithms, ngrams, trigrams, natural language processing, NLP Note: Work carried out under theme SEN4 "Evolutionary Computation". To appear in Late breaking papers of GECCO'2000: Proceedings of the Genetic and Evolutionary Computation Conference. This research was part of the "Autonomous Systems of Trade Agents in E-Commerce" project, f...
Keyphrases
evolutionary nearest neighbour classifier natural language text classification genetic algorithm binary classification nlp note short multi-author technical english document nearest neighbour classifier mathematics subject classification late breaking paper evolutionary computation conference acm computing classification system trade agent several class e-commerce project theme sen4 evolutionary computation autonomous system natural language processing ngram vector zipf law single pas
