Grammatical category disambiguation by statistical optimization
Computational Linguistics
Foundations of statistical natural language processing
Foundations of statistical natural language processing
Statistical Language Learning
Modern Information Retrieval
Part-of-Speech Tagging with Evolutionary Algorithms
CICLing '02 Proceedings of the Third International Conference on Computational Linguistics and Intelligent Text Processing
The Journal of Machine Learning Research
Building a large annotated corpus of English: the penn treebank
Computational Linguistics - Special issue on using large corpora: II
Improving accuracy in word class tagging through the combination of machine learning systems
Computational Linguistics
TnT: a statistical part-of-speech tagger
ANLC '00 Proceedings of the sixth conference on Applied natural language processing
Improving part-of-speech tagging using lexicalized HMMs
Natural Language Engineering
Tagging and chunking with bigrams
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 2
Parallel Metaheuristics: A New Class of Algorithms
Parallel Metaheuristics: A New Class of Algorithms
Feasibility-preserving crossover for maximum k-coverage problem
Proceedings of the 10th annual conference on Genetic and evolutionary computation
How evolutionary algorithms are applied to statistical natural language processing
Artificial Intelligence Review
Intelligent steganalytic system: application on natural language environment
WSEAS Transactions on Systems and Control
Evolutionary undersampling for classification with imbalanced datasets: Proposals and taxonomy
Evolutionary Computation
Classifier Ensemble Selection Using Genetic Algorithm for Named Entity Recognition
Research on Language and Computation
Evolutionary Shallow Natural Language Parsing
Computational Intelligence
Hi-index | 0.89 |
This work analyzes the relative advantages of different metaheuristic approaches to the well-known natural language processing problem of part-of-speech tagging. This consists of assigning to each word of a text its disambiguated part-of-speech according to the context in which the word is used. We have applied a classic genetic algorithm (GA), a CHC algorithm, and a simulated annealing (SA). Different ways of encoding the solutions to the problem (integer and binary) have been studied, as well as the impact of using parallelism for each of the considered methods. We have performed experiments on different linguistic corpora and compared the results obtained against other popular approaches plus a classic dynamic programming algorithm. Our results claim for the high performances achieved by the parallel algorithms compared to the sequential ones, and state the singular advantages for every technique. Our algorithms and some of its components can be used to represent a new set of state-of-the-art procedures for complex tagging scenarios.