Designing a verb guesser for part of speech tagging in Northern Sotho

Abstract

The aim of this article is to describe the design and implementation of a verb guesser that wiil enhance the results of statistical part of speech (POS) tagging of verbs in Northern Sotho. It wiil be illustrated that verb stems in Northern Sotho can successfully be recognised by examining their suffixes and combinations of suffixes. Two approaches to verbal derivation analysis will be utilised, namely morphological analysis and corpus querying of suffixes and combinations of suffixes.

Designing a noun guesser for part of speech tagging in Northern Sotho

“…The remaining 604 types were first submitted to our verb guesser (cf. Prinsloo et al, 2008). Candidates that were possibly considered to be ambiguous between verbs and nouns were then analysed by the noun guesser.…”

“…The noun guesser is conceived as a step preceding the use of the abovementioned statistical tool: it dynamically provides lexical data for the tagger, so as to make the task of the statistical tagger somewhat easier. In this, the objective is similar to that of the verb guesser, as discussed in Prinsloo, Taljard, Heid and Faaß (2008). For an analysis of verbal extension sequencing, see Anderson and Kotzé (2008).…”