R: Convert Penn TreeBank POS to Universal Tagset

universalTagset {coreNLP}

R Documentation

Convert Penn TreeBank POS to Universal Tagset

Description

Maps a character string of English Penn TreeBank part of speech tags into the universal tagset codes. This provides a reduced set of tags (12), and a better cross-linguist model of speech.

Usage

universalTagset(pennPOS)

Arguments

pennPOS

a character vector of penn tags to match

Examples

tok <- getToken(annoEtranger)
cbind(tok$POS,universalTagset(tok$POS))

[Package coreNLP version 0.4-3 Index]