# Diversified Hidden Markov Models for Sequential Labeling

## TL;DR

This paper introduces diversified Hidden Markov Models (dHMM) that incorporate a diversity-encouraging prior to improve sequential labeling tasks like PoS tagging and OCR, demonstrating competitive results on benchmark datasets.

## Contribution

The paper proposes a novel dHMM extension using a determinantal point process prior to enhance dynamic sequential labeling performance.

## Key findings

- dHMM outperforms traditional HMM in benchmark tests.
- Effective in both unsupervised PoS tagging and supervised OCR.
- Achieves competitive results with state-of-the-art methods.

## Abstract

Labeling of sequential data is a prevalent meta-problem for a wide range of real world applications. While the first-order Hidden Markov Models (HMM) provides a fundamental approach for unsupervised sequential labeling, the basic model does not show satisfying performance when it is directly applied to real world problems, such as part-of-speech tagging (PoS tagging) and optical character recognition (OCR). Aiming at improving performance, important extensions of HMM have been proposed in the literatures. One of the common key features in these extensions is the incorporation of proper prior information. In this paper, we propose a new extension of HMM, termed diversified Hidden Markov Models (dHMM), which utilizes a diversity-encouraging prior over the state-transition probabilities and thus facilitates more dynamic sequential labellings. Specifically, the diversity is modeled by a continuous determinantal point process prior, which we apply to both unsupervised and supervised scenarios. Learning and inference algorithms for dHMM are derived. Empirical evaluations on benchmark datasets for unsupervised PoS tagging and supervised OCR confirmed the effectiveness of dHMM, with competitive performance to the state-of-the-art.