Probabilistic Tagging with Feature Structures

TL;DR

This paper introduces a probabilistic tagging method using feature-structured tags within a hidden Markov model, which is especially effective for morphologically rich languages with limited training data.

Contribution

It presents a novel approach that leverages feature structures for tagging, improving performance in scenarios with small corpora and large tag sets.

Findings

Effective for morphologically rich languages

Performs well with limited training data

Utilizes feature-value-pairs for contextual probabilities

Abstract

The described tagger is based on a hidden Markov model and uses tags composed of features such as part-of-speech, gender, etc. The contextual probability of a tag (state transition probability) is deduced from the contextual probabilities of its feature-value-pairs. This approach is advantageous when the available training corpus is small and the tag set large, which can be the case with morphologically rich languages.