"Natural" is a general natural language facility for nodejs. It offers a broad range of functionalities for natural language processing. Tokenizing, stemming, classification, phonetics, tf-idf, WordNet, string similarity, and some inflections are currently supported. It’s still in the early stages, so we’re very interested in bug reports, contributions and the like. Note that many algorithms from Rob Ellis’s node-nltools are being merged into this project and will be maintained from here onward. While most of the algorithms are English-specific, contributors have implemented support for other languages. Russian stemming has been added and Spanish stemming has been added, as well. Stemming and tokenizing in more languages have been added. If you’re just looking to use natural without your own node application, you can install via NPM.
Features
- Word, Regexp, and Treebank tokenizers are provided for breaking text up into arrays of tokens
- Natural provides an implementation of three algorithms for calculating string distance, Hamming distance, Jaro-Winkler, Levenshtein distance, and Dice coefficient
- Currently stemming is supported via the Porter and Lancaster (Paice/Husk) algorithms
- Two classifiers are currently supported, Naive Bayes and logistic regression
- The Maximum Entropy Classifier module provides a classifier based on maximum entropy modelling
- Offers a simple sentiment analysis algorithm based on a vocabulary that assigns polarity to words
Project Samples
