11

我正在尝试并行使用 openNLP/NLP 包中的词性标记。我需要代码才能在任何操作系统上工作，因此我选择parLapply并行使用该功能（但对其他独立于操作系统的选项持开放态度）。过去我tagPOS从 openNLP 包中运行函数parLapply没有问题。然而，openNLP 包最近进行了一些更改，消除tagPOS并添加了一些更灵活的选项。Kurt 很友善地帮助我tagPOS从新包的工具中重新创建了该功能。我可以得到lapply版本工作，但不是并行版本。它一直说节点需要更多的变量传递给它们，直到它最终从 openNLP 请求一个非导出函数。这似乎很奇怪，它会不断要求传递越来越多的变量，这告诉我我设置parLapply不正确。如何设置tagPOS以并行、独立于操作系统的方式运行？

library(openNLP)
library(NLP)
library(parallel)

## POS tagger
tagPOS <-  function(x, pos_tag_annotator, ...) {
    s <- as.String(x)
    ## Need sentence and word token annotations.
    word_token_annotator <- Maxent_Word_Token_Annotator()
    a2 <- Annotation(1L, "sentence", 1L, nchar(s))
    a2 <- annotate(s, word_token_annotator, a2)
    a3 <- annotate(s, pos_tag_annotator, a2)

    ## Determine the distribution of POS tags for word tokens.
    a3w <- a3[a3$type == "word"]
    POStags <- unlist(lapply(a3w$features, `[[`, "POS"))

    ## Extract token/POS pairs (all of them): easy.
    POStagged <- paste(sprintf("%s/%s", s[a3w], POStags), collapse = " ")
    list(POStagged = POStagged, POStags = POStags)
} ## End of tagPOS function 

## Set up a parallel run
text.var <- c("I like it.", "This is outstanding soup!",  
    "I really must get the recipe.")
ntv <- length(text.var)
PTA <- Maxent_POS_Tag_Annotator()   

cl <- makeCluster(mc <- getOption("cl.cores", detectCores()/2))
clusterExport(cl=cl, varlist=c("text.var", "ntv", 
    "tagPOS", "PTA", "as.String", "Maxent_Word_Token_Annotator"), 
    envir = environment())
m <- parLapply(cl, seq_len(ntv), function(i) {
        x <- tagPOS(text.var[i], PTA)
        return(x)
    }
)
stopCluster(cl)

## Error in checkForRemoteErrors(val) : 
##   3 nodes produced errors; first error: could not find function 
##   "Maxent_Simple_Word_Tokenizer"

openNLP::Maxent_Simple_Word_Tokenizer

## >openNLP::Maxent_Simple_Word_Tokenizer
## Error: 'Maxent_Simple_Word_Tokenizer' is not an exported 
##     object from 'namespace:openNLP'

## It's a non exported function
openNLP:::Maxent_Simple_Word_Tokenizer


## Demo that it works with lapply
lapply(seq_len(ntv), function(i) {
    tagPOS(text.var[i], PTA)
})

lapply(text.var, function(x) {
    tagPOS(x, PTA)
})

## >     lapply(seq_len(ntv), function(i) {
## +         tagPOS(text.var[i], PTA)
## +     })
## [[1]]
## [[1]]$POStagged
## [1] "I/PRP like/IN it/PRP ./."
## 
## [[1]]$POStags
## [1] "PRP" "IN"  "PRP" "."  
## 
## [[1]]$word.count
## [1] 3
## 
## 
## [[2]]
## [[2]]$POStagged
## [1] "THis/DT is/VBZ outstanding/JJ soup/NN !/."
## 
## [[2]]$POStags
## [1] "DT"  "VBZ" "JJ"  "NN"  "."  
## 
## [[2]]$word.count
## [1] 4
## 
## 
## [[3]]
## [[3]]$POStagged
## [1] "I/PRP really/RB must/MD get/VB the/DT recip/NN ./."
## 
## [[3]]$POStags
## [1] "PRP" "RB"  "MD"  "VB"  "DT"  "NN"  "."  
## 
## [[3]]$word.count
## [1] 6

编辑：根据史蒂夫的建议

请注意，openNLP 是全新的。我从 CRAN 的 tar.gz 安装了 2.1 版。即使此功能存在，我也会收到以下错误。

library(openNLP); library(NLP); library(parallel)

tagPOS <-  function(text.var, pos_tag_annotator, ...) {
    s <- as.String(text.var)

    ## Set up the POS annotator if missing (for parallel)
    if (missing(pos_tag_annotator)) {
        PTA <- Maxent_POS_Tag_Annotator()
    }

    ## Need sentence and word token annotations.
    word_token_annotator <- Maxent_Word_Token_Annotator()
    a2 <- Annotation(1L, "sentence", 1L, nchar(s))
    a2 <- annotate(s, word_token_annotator, a2)
    a3 <- annotate(s, PTA, a2)

    ## Determine the distribution of POS tags for word tokens.
    a3w <- a3[a3$type == "word"]
    POStags <- unlist(lapply(a3w$features, "[[", "POS"))

    ## Extract token/POS pairs (all of them): easy.
    POStagged <- paste(sprintf("%s/%s", s[a3w], POStags), collapse = " ")
    list(POStagged = POStagged, POStags = POStags)
}

text.var <- c("I like it.", "This is outstanding soup!",  
    "I really must get the recipe.")

cl <- makeCluster(mc <- getOption("cl.cores", detectCores()/2))
clusterEvalQ(cl, {library(openNLP); library(NLP)})
m <- parLapply(cl, text.var, tagPOS)

## > m <- parLapply(cl, text.var, tagPOS)
## Error in checkForRemoteErrors(val) : 
##   3 nodes produced errors; first error: could not find function "Maxent_POS_Tag_Annotator"

stopCluster(cl)


> packageDescription('openNLP')
Package: openNLP
Encoding: UTF-8
Version: 0.2-1
Title: Apache OpenNLP Tools Interface
Authors@R: person("Kurt", "Hornik", role = c("aut", "cre"), email =
          "Kurt.Hornik@R-project.org")
Description: An interface to the Apache OpenNLP tools (version 1.5.3).  The Apache OpenNLP
          library is a machine learning based toolkit for the processing of natural language
          text written in Java.  It supports the most common NLP tasks, such as tokenization,
          sentence segmentation, part-of-speech tagging, named entity extraction, chunking,
          parsing, and coreference resolution.  See http://opennlp.apache.org/ for more
          information.
Imports: NLP (>= 0.1-0), openNLPdata (>= 1.5.3-1), rJava (>= 0.6-3)
SystemRequirements: Java (>= 5.0)
License: GPL-3
Packaged: 2013-08-20 13:23:54 UTC; hornik
Author: Kurt Hornik [aut, cre]
Maintainer: Kurt Hornik <Kurt.Hornik@R-project.org>
NeedsCompilation: no
Repository: CRAN
Date/Publication: 2013-08-20 15:41:22
Built: R 3.0.1; ; 2013-08-20 13:48:47 UTC; windows
4

1 回答 1

7

由于您是从NLP集群工作人员上调用函数，因此您应该在调用之前将其加载到每个工作人员上parLapply。您可以从工作函数中执行此操作，但我倾向于在创建集群对象之后使用clusterCall或立即使用：clusterEvalQ

clusterEvalQ(cl, {library(openNLP); library(NLP)})

由于as.String和Maxent_Word_Token_Annotator在这些包中，它们不应该被导出。

请注意，在我的机器上运行您的示例时，我注意到该PTA对象在导出到工作机器后不起作用。据推测，该对象中有一些东西无法安全地序列化和反序列化。在我使用 为工人创建该对象后clusterEvalQ，该示例成功运行。在这里，使用 openNLP 0.2-1：

library(parallel)
tagPOS <-  function(x, ...) {
    s <- as.String(x)
    word_token_annotator <- Maxent_Word_Token_Annotator()
    a2 <- Annotation(1L, "sentence", 1L, nchar(s))
    a2 <- annotate(s, word_token_annotator, a2)
    a3 <- annotate(s, PTA, a2)
    a3w <- a3[a3$type == "word"]
    POStags <- unlist(lapply(a3w$features, `[[`, "POS"))
    POStagged <- paste(sprintf("%s/%s", s[a3w], POStags), collapse = " ")
    list(POStagged = POStagged, POStags = POStags)
}
text.var <- c("I like it.", "This is outstanding soup!",
    "I really must get the recipe.")
cl <- makeCluster(mc <- getOption("cl.cores", detectCores()/2))
clusterEvalQ(cl, {
    library(openNLP)
    library(NLP)
    PTA <- Maxent_POS_Tag_Annotator()
})
m <- parLapply(cl, text.var, tagPOS)
print(m)
stopCluster(cl)

如果clusterEvalQ因为找不到 Maxent_POS_Tag_Annotator 而失败，则可能是在工作人员上加载了错误版本的 openNLP。sessionInfo您可以通过执行以下命令来确定您在工作人员身上获得的软件包版本clusterEvalQ：

library(parallel)
cl <- makeCluster(2)
clusterEvalQ(cl, {library(openNLP); library(NLP)})
clusterEvalQ(cl, sessionInfo())

这将返回sessionInfo()在每个集群工作人员上执行的结果。以下是我正在使用且对我有用的一些软件包的版本信息：

other attached packages:
[1] NLP_0.1-0     openNLP_0.2-1

loaded via a namespace (and not attached):
[1] openNLPdata_1.5.3-1 rJava_0.9-4
于 2013-08-21T13:33:02.893 回答