udpipe_bab: Perform Parts of Speech tagging and Lemmatisation on...

In DIGI-VUB/udpipe.bab: UDPipe Models Built on Brieven als Buit

Description

Perform Parts of Speech tagging and Lemmatisation on 18th-19th century Dutch texts

Usage

udpipe_bab(x, tokenizer = c("generic", "basic"), trace = FALSE, ...)

Arguments

x	a data.frame with columns doc_id and text
tokenizer	either 'generic' to use a generic tokenizer provided by R package udpipe or 'basic' to split based on spaces
trace	argument passed on to udpipe_annotate
...	passed on to tokenize_simple

Value

a data.frame with tokenised and parts of speech tags and lemma's with columns doc_id, sentence_id, token, lemma, upos, xpos, token_id, term_id, start, end. Note that columns start and end will be all NA values if the 'basic' tokenizer is used

See Also

tokenize_simple, udpipe_annotate

Examples

x <- data.frame(doc_id = c("a", "b"), 
                text = c("Desen brief sal men bstelen an Janetie Alberts woont in fredrickstadt", 
                         "dit kan Ul op vaders rekeningh setten ende senden"), 
                stringsAsFactors = FALSE)
anno <- udpipe_bab(x, tokenizer = "generic")
anno
anno <- udpipe_bab(x, tokenizer = "basic")
anno

DIGI-VUB/udpipe.bab documentation built on Sept. 9, 2020, 12:35 a.m.