按空格拆分，然后使用shift键 * 粘贴 *：

s <- unlist(strsplit(string, " ", fixed = TRUE))
sl <- length(s)
paste(s[1:(sl-1)], s[2:sl])
# [1] "A B" "B C" "C D" "D E" "E F"

tmp <- strsplit(string, " ")[[1]]
tmp
# [1] "A" "B" "C" "D" "E" "F"
sapply(seq_along(tmp)[-1], function(z) paste(tmp[z-1:0], collapse = " "))
# [1] "A B" "B C" "C D" "D E" "E F"

如果你已经使用了一些文本挖掘包（如清理、词干化和删除停用词），很可能会有一些东西生成n-gram（而不仅仅是bigram）。

string <- "A B C D E F"

quanteda::tokens_ngrams(quanteda::tokens(string), concatenator = " ")
#> Tokens consisting of 1 document.
#> text1 :
#> [1] "A B" "B C" "C D" "D E" "E F"

data.frame(s = string) |>
  tidytext::unnest_ngrams(input = "s", output = "bigrams", n = 2)
#>   bigrams
#> 1     a b
#> 2     b c
#> 3     c d
#> 4     d e
#> 5     e f

创建于2023年1月31日，使用reprex v2.0.2

一个选项是使用带有look ahead的正则表达式。

string <- "A B C D E F"

. <- gregexpr("\\S+\\s+(?=(\\S+))", string, perl=TRUE)[[1]]
attr(.,"match.length") <- attr(.,"match.length") + attr(., "capture.length")
regmatches(string, list(.))[[1]]
#[1] "A B" "B C" "C D" "D E" "E F"