Joint PoS Tagging and Stemming for Agglutinative Languages

TL;DR

This paper introduces an unsupervised Bayesian HMM model that jointly performs PoS tagging and stemming to address sparsity issues in agglutinative languages, demonstrating improved tagging accuracy for Turkish and Finnish.

Contribution

It proposes a novel joint PoS tagging and stemming model using Bayesian HMMs specifically designed for agglutinative languages, enhancing performance over separate approaches.

Findings

Joint model improves PoS tagging accuracy

Effective in Turkish and Finnish languages

Demonstrates benefits for morphologically rich languages

Abstract

The number of word forms in agglutinative languages is theoretically infinite and this variety in word forms introduces sparsity in many natural language processing tasks. Part-of-speech tagging (PoS tagging) is one of these tasks that often suffers from sparsity. In this paper, we present an unsupervised Bayesian model using Hidden Markov Models (HMMs) for joint PoS tagging and stemming for agglutinative languages. We use stemming to reduce sparsity in PoS tagging. Two tasks are jointly performed to provide a mutual benefit in both tasks. Our results show that joint POS tagging and stemming improves PoS tagging scores. We present results for Turkish and Finnish as agglutinative languages and English as a morphologically poor language.