Tagging the Teleman Corpus

TL;DR

This paper compares the difficulty of tagging the Swedish Teleman corpus with English Susanne corpus using HMM-based and novel taggers, finding Teleman tagging more challenging with similar tagger performance.

Contribution

It introduces a novel reductionistic statistical tagger and compares its performance with HMM-based taggers on two different language corpora.

Findings

Tagging the Teleman corpus is more difficult than Susanne.

Both taggers perform similarly across corpora.

The novel tagger is competitive with HMM-based methods.

Abstract

Experiments were carried out comparing the Swedish Teleman and the English Susanne corpora using an HMM-based and a novel reductionistic statistical part-of-speech tagger. They indicate that tagging the Teleman corpus is the more difficult task, and that the performance of the two different taggers is comparable.