Question

我正在尝试做一个非常简单的词来源于R并得到一些非常意外的东西。在下面的代码中＆＃39;完成＆＃39;变量是＆＃39; NA＆＃39;。为什么我不能简单地完成词干？

library(tm) 
library(SnowballC)
dict <- c("easy")
stem <- stemDocument(dict, language = "english")
complete <- stemCompletion(stem, dictionary=dict)

谢谢！

Answer 1

您可以使用stemCompletion()查看tm:::stemCompletion功能的内部。

function (x, dictionary, type = c("prevalent", "first", "longest", "none", "random", "shortest")){
if(inherits(dictionary, "Corpus")) 
  dictionary <- unique(unlist(lapply(dictionary, words)))
type <- match.arg(type)
possibleCompletions <- lapply(x, function(w) grep(sprintf("^%s",w), dictionary, value = TRUE))
switch(type, first = {
  setNames(sapply(possibleCompletions, "[", 1), x)
}, longest = {
  ordering <- lapply(possibleCompletions, function(x) order(nchar(x), 
      decreasing = TRUE))
  possibleCompletions <- mapply(function(x, id) x[id], 
      possibleCompletions, ordering, SIMPLIFY = FALSE)
  setNames(sapply(possibleCompletions, "[", 1), x)
}, none = {
  setNames(x, x)
}, prevalent = {
  possibleCompletions <- lapply(possibleCompletions, function(x) sort(table(x), 
      decreasing = TRUE))
  n <- names(sapply(possibleCompletions, "[", 1))
  setNames(if (length(n)) n else rep(NA, length(x)), x)
}, random = {
  setNames(sapply(possibleCompletions, function(x) {
      if (length(x)) sample(x, 1) else NA
  }), x)
}, shortest = {
  ordering <- lapply(possibleCompletions, function(x) order(nchar(x)))
  possibleCompletions <- mapply(function(x, id) x[id], 
      possibleCompletions, ordering, SIMPLIFY = FALSE)
  setNames(sapply(possibleCompletions, "[", 1), x)
})

}

x参数是您的词干，dictionary是未被限制的。唯一重要的是第五行;它对字典术语列表中的词干进行简单的正则表达式匹配。

possibleCompletions <- lapply(x, function(w) grep(sprintf("^%s",w), dictionary, value = TRUE))

因此它失败了，因为它无法找到＆＃34; easi＆＃34;用＆＃34;轻松＆＃34;。如果你也有'＃34;最简单的＆＃34;在你的字典中，两个术语都匹配，因为现在有一个字典单词，开头有四个相同的字母。

library(tm) 
library(SnowballC)
dict <- c("easy","easiest")
stem <- stemDocument(dict, language = "english")
complete <- stemCompletion(stem, dictionary=dict)
complete
     easi   easiest 
"easiest" "easiest"

Answer 2

wordStem()似乎这样做..

library(tm) 
library(SnowballC)
dict <- c("easy")
> wordStem(dict)
[1] "easi"

r中的词干不能按预期工作

2 个答案: