TnT - A Statistical Part-of-Speech Tagger

Details TnT - A Statistical Part-of-Speech Tagger TnT - A Statistical Part-of-Speech Tagger

2000-03-13

arxiv.org/abs/cs/0003055v1

Proceedings of ANLP-2000, Seattle, WA

Computer Science

Computation and Language

8 pages

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

TnT - A Statistical Part-of-Speech Tagger does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with TnT - A Statistical Part-of-Speech Tagger, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and TnT - A Statistical Part-of-Speech Tagger will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-148937