package wseg

  1. Overview
  2. Docs
Legend:
Library
Module
Module type
Parameter
Class
Class type

MMSEg: A Word Identification System Based on the Maximum Matching Algorithm.

val rule1 : Dict.chunk list -> Dict.chunk list

MMSEG rule1: maximum matching

val rule2 : Dict.chunk list -> Dict.chunk list

MMSEG rule2: largest average word length

val rule3 : Dict.chunk list -> Dict.chunk list

MMSEG rule3: smallest variance of word lengths

val rule4 : Dict.chunk list -> Dict.chunk list

MMSEG rule4: largest sum of probability of the chain of all words

val rule_final : Dict.chunk list -> Dict.chunk option

rule final, List.hd

val seg : Dict.chunk list -> Dict.chunk option

apply rule1 .. rule4 .. rule final to a chunk list