createHMM: Create a HMM model from corpus.

In Rwordseg: Chinese Word Segmentation

Description

Read a corpus vector and generate a HMM model file.

Usage

createHMM(trainvec, outputfolder = NULL, sensplit = "/w",
  wordsplit = "\\s+", natruesplit = "/", removestr = "^.*?/m")

Arguments

trainvec	A character vector of corpus.
outputfolder	The folder of output file. Defult is NULL.
sensplit	Character containing regular expression to use for splitting sentence.
wordsplit	Character containing regular expression to use for splitting words.
natruesplit	Character containing regular expression to use for splitting nature.
removestr	Character containing regular expression to use for removing string.

Value

a list from initHMM.

Examples

data(PD980105)
m1 <- createHMM(PD980105[1:10])
names(m1)

Rwordseg documentation built on Aug. 17, 2019, 3 p.m.