Created
June 24, 2015 07:10
-
-
Save dcbartlett/221200796a239b8cfca7 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var nlp = require('./nlp'); | |
var tokens = nlp.tokenize("Eligibility: Open to the general public, must have a library card to checkout library materials"); | |
console.log(tokens.tag()); | |
//Outputs "Open" as "NNP" | |
var tokens = nlp.tokenize("Eligibility: open to the general public, must have a library card to checkout library materials"); | |
console.log(tokens.tag()); | |
//Outputs "open" as "JJ" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
var pos = require('pos'); | |
var _ = require('lodash'); | |
module.exports = { | |
tokenize: function (string) { | |
this.tokens = new pos.Lexer().lex(string); | |
return this; | |
}, | |
tag: function (tokens) { | |
if (!tokens) { | |
var tokens = this.tokens; | |
} | |
var taggedTokens = []; | |
_.each(new pos.Tagger().tag(tokens), function(taggedToken) { | |
var taggedToken = { | |
token: taggedToken[0], | |
tag: taggedToken[1] | |
} | |
taggedTokens.push(taggedToken); | |
}); | |
return taggedTokens; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment