Question

我的文字如下。

   Section <- c("If an infusion reaction occurs, interrupt the infusion.")
    df <- data.frame(Section)

当我使用tidytext和下面的代码标记时，

AA <- df %>%
  mutate(tokens = str_extract_all(df$Section, "([^\\s]+)"),
         locations = str_locate_all(df$Section, "([^\\s]+)"),
         locations = map(locations, as.data.frame)) %>%
  select(-Section) %>%
  unnest(tokens, locations)

它给了我令牌，开始和结束位置。如何在同时取消嵌套的同时获取POS标签。如下所示（下图中的POS标签可能不正确）

Answer 1

您可以使用udpipe软件包获取POS数据。 Udpipe自动将标点符号化。

@for(var i = 0; i < 5; i++)

  Your code goes here using thing[i]

现在将其合并为您要求的previous question的结果。我回答了其中一个。

Section <- c("If an infusion reaction occurs, interrupt the infusion.")
df <- data.frame(Section, stringAsFactors = FALSE)

library(udpipe)
library(dplyr)
udmodel <- udpipe_download_model(language = "english")
udmodel <- udpipe_load_model(file = udmodel$file_model)


x <- udpipe_annotate(udmodel, 
                     df$Section)
x <- as.data.frame(x)

x %>% select(token, upos)
       token  upos
1         If SCONJ
2         an   DET
3   infusion  NOUN
4   reaction  NOUN
5     occurs  NOUN
6          , PUNCT
7  interrupt  VERB
8        the   DET
9   infusion  NOUN
10         . PUNCT

编辑：更好的解决方案

但是最好的解决方案是从udpipe开始，然后再进行其余操作。请注意，我使用的是stringi而不是stringr包。 stringr基于stringi，但是stringi具有更多选项。

library(stringr)
library(purrr)
library(tidyr)

df %>% mutate(
  tokens = str_extract_all(Section, "\\w+|[[:punct:]]"),
  locations = str_locate_all(Section, "\\w+|[[:punct:]]"),
  locations = map(locations, as.data.frame)) %>%
  select(-Section) %>%
  unnest(tokens, locations) %>% 
  mutate(POS = purrr::map_chr(tokens, function(x) as.data.frame(udpipe_annotate(udmodel, x = x, tokenizer = "vertical"))$upos))

       tokens start end  upos
1         If     1   2 SCONJ
2         an     4   5   DET
3   infusion     7  14  NOUN
4   reaction    16  23  NOUN
5     occurs    25  30  NOUN
6          ,    31  31 PUNCT
7  interrupt    33  41  VERB
8        the    43  45   DET
9   infusion    47  54  NOUN
10         .    55  55 PUNCT

Answer 2

仅供参考。从CRAN的udpipe版本0.7开始，您可以执行以下操作。

library(udpipe)
x <- data.frame(doc_id = c("doc1", "doc2"),
                text = c("If an infusion reaction occurs, interrupt the infusion.",
                         "Houston we have a problem"))
x <- udpipe(x, "english")
x

为您提供（注意您要查找的开始/结束以及令牌/ upos / xpos）：

 doc_id paragraph_id sentence_id start end term_id token_id     token     lemma  upos xpos                                      feats head_token_id   dep_rel deps            misc
   doc1            1           1     1   2       1        1        If        if SCONJ   IN                                       <NA>             7      mark <NA>            <NA>
   doc1            1           1     4   5       2        2        an         a   DET   DT                  Definite=Ind|PronType=Art             5       det <NA>            <NA>
   doc1            1           1     7  14       3        3  infusion  infusion  NOUN   NN                                Number=Sing             4  compound <NA>            <NA>
   doc1            1           1    16  23       4        4  reaction  reaction  NOUN   NN                                Number=Sing             5  compound <NA>            <NA>
   doc1            1           1    25  30       5        5    occurs     occur  NOUN  NNS                                Number=Plur             7     nsubj <NA>   SpaceAfter=No
   doc1            1           1    31  31       6        6         ,         , PUNCT    ,                                       <NA>             7     punct <NA>            <NA>
   doc1            1           1    33  41       7        7 interrupt interrupt  VERB   VB                      Mood=Imp|VerbForm=Fin             0      root <NA>            <NA>
   doc1            1           1    43  45       8        8       the       the   DET   DT                  Definite=Def|PronType=Art             9       det <NA>            <NA>
   doc1            1           1    47  54       9        9  infusion  infusion  NOUN   NN                                Number=Sing             7       obj <NA>   SpaceAfter=No
   doc1            1           1    55  55      10       10         .         . PUNCT    .                                       <NA>             7     punct <NA> SpacesAfter=\\n
   doc2            1           1     1   7       1        1   Houston   Houston PROPN  NNP                                Number=Sing             0      root <NA>            <NA>
   doc2            1           1     9  10       2        2        we        we  PRON  PRP Case=Nom|Number=Plur|Person=1|PronType=Prs             3     nsubj <NA>            <NA>
   doc2            1           1    12  15       3        3      have      have  VERB  VBP           Mood=Ind|Tense=Pres|VerbForm=Fin             1 parataxis <NA>            <NA>
   doc2            1           1    17  17       4        4         a         a   DET   DT                  Definite=Ind|PronType=Art             5       det <NA>            <NA>
   doc2            1           1    19  25       5        5   problem   problem  NOUN   NN                                Number=Sing             3       obj <NA> SpacesAfter=\\n

Answer 3

就像上一个回答者一样，我认为udpipe可能是进行POS标记的最简单方法。我最喜欢的与udpipe交互的方式是通过cleanNLP包。调用初始化函数后，只需两行代码即可获得udpipe输出。

library(tidyverse)
library(cleanNLP)

cnlp_init_udpipe()
#> Loading required namespace: udpipe

df <- data_frame(id = 1,
                 text = c("If an infusion reaction occurs, interrupt the infusion."))

cnlp_annotate(df) %>%
  cnlp_get_tif()
#> # A tibble: 10 x 19
#>    id      sid   tid word  lemma upos  pos     cid   pid definite mood 
#>    <chr> <int> <int> <chr> <chr> <chr> <chr> <dbl> <int> <chr>    <chr>
#>  1 1         1     1 If    if    SCONJ IN        0     1 <NA>     <NA> 
#>  2 1         1     2 an    a     DET   DT        3     1 Ind      <NA> 
#>  3 1         1     3 infu… infu… NOUN  NN        6     1 <NA>     <NA> 
#>  4 1         1     4 reac… reac… NOUN  NN       15     1 <NA>     <NA> 
#>  5 1         1     5 occu… occur NOUN  NNS      24     1 <NA>     <NA> 
#>  6 1         1     6 ,     ,     PUNCT ,        30     1 <NA>     <NA> 
#>  7 1         1     7 inte… inte… VERB  VB       32     1 <NA>     Imp  
#>  8 1         1     8 the   the   DET   DT       42     1 Def      <NA> 
#>  9 1         1     9 infu… infu… NOUN  NN       46     1 <NA>     <NA> 
#> 10 1         1    10 .     .     PUNCT .        54     1 <NA>     <NA> 
#> # ... with 8 more variables: number <chr>, pron_type <chr>,
#> #   verb_form <chr>, source <int>, relation <chr>, word_source <chr>,
#> #   lemma_source <chr>, spaces <dbl>

由reprex package（v0.2.0）于2018-08-15创建。

一次性进行R POS标记和标记

3 个答案: