TnT - A Statistical Part-of-Speech Tagger

TLDR

Trigrams'n'Tags (TnT) is an efficient statistical part‑of‑speech tagger. The authors argue that a Markov‑model tagger performs at least as well as other approaches, describe its basic model and smoothing techniques, and present evaluations on two corpora. The tagger uses a Markov model with smoothing techniques and methods for handling unknown words. A recent comparison shows that TnT performs significantly better than other approaches on the tested corpora.

Abstract

Trigrams'n'Tags (TnT) is an efficient statistical part-of-speech tagger. Contrary to claims found elsewhere in the literature, we argue that a tagger based on Markov models performs at least as well as other current approaches, including the Maximum Entropy framework. A recent comparison has even shown that TnT performs significantly better for the tested corpora. We describe the basic model of TnT, the techniques used for smoothing and for handling unknown words. Furthermore, we present evaluations on two corpora.