Integrate recipe to annotate sentences with openNLP

[ablaette]

The vignette on sentence annotation explains how you can use an existing POS annotation with the STTS to generate an annotation of sentences.

This chunk of code explains what you can do to use openNLP. However, it is somewhat slow at the very end. This is why I hesitate to integrate it into the vignette.

library(RcppCWB)
library(NLP)
library(openNLP)

corpus_size <- cl_attribute_size("UNGA", attribute = "word", attribute_type ="p")
cpos <- 0L:(corpus_size - 1L)
ids <- cl_cpos2id("UNGA", p_attribute = "word", cpos = cpos)
word <- cl_id2str("UNGA", p_attribute = "word", id = ids)

whitespace_after <- c(ifelse(word %in% c(".", ",", ":", "!", "?", ";"), FALSE, TRUE)[2L:length(word)], FALSE)
word_with_whitespace <- paste(word, ifelse(whitespace_after, " ", ""), sep = "")
s <- String(paste(word_with_whitespace, collapse = ""))

word_length <- sapply(word, nchar)
left_offset <- c(1L, (cumsum(sapply(word_with_whitespace, nchar)) + 1L)[1L:(length(word) - 1L)] )
right_offset <- left_offset + word_length - 1L
word_annotation <- NLP::Annotation(
  id = cpos,
  rep.int("word", length(cpos)),
  start = left_offset,
  end = right_offset
)

sent_token_annotator <- Maxent_Sent_Token_Annotator()
sentence_annotation <- annotate(s, sent_token_annotator)

a <- c(word_annotation, sentence_annotation)

sentences_cpos <- lapply(annotations_in_spans(a[a$type == "word"], a[a$type == "sentence"]), function(a) a$id)
region_matrix <- do.call(rbind, lapply(sentences_cpos, function(cpos) c(cpos[1L], cpos[length(cpos)])))