Created
August 4, 2012 03:55
-
-
Save beala/3254234 to your computer and use it in GitHub Desktop.
n-gram
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
// Some Scala implementations of concepts from "Natural Language Processing For The Working Programmer" | |
// http://nlpwp.org/book/chap-ngrams.xhtml | |
/** | |
* Return all lists of n adjacent words. | |
* ngram("I love Scala!", 2) = List(List(I, love), List(love, Scala!) | |
*/ | |
def ngram(sent:String, n:Int):List[List[String]]={ | |
def helper(sent:List[String]):List[List[String]] = { | |
sent match{ | |
case(h::t) if(sent.length >= n) => sent.take(n) :: helper(t) | |
case(_) => Nil | |
} | |
} | |
helper(sent.split(' ').toList) | |
} | |
println(ngram("I love Scala!", 2)) | |
/** | |
* Return all pairs of words where the first word comes before the second word. | |
* skipBigram("I love Scala!") == List(List(I, love), List(I, Scala!), List(love, Scala!)) | |
*/ | |
def skipBigram(sent:String):List[List[String]]={ | |
def helper(sent:List[String]):List[List[String]]={ | |
sent match{ | |
case(h::t) => (for(word:String <- t) yield List(h, word)) ++ helper(t) | |
case(Nil) => Nil | |
} | |
} | |
return helper(sent.split(' ').toList) | |
} | |
println(skipBigram("I love Scala!")) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment