Inference with constrained hidden Markov models in PRISM

Henning Christiansen, Christian Theil Have, Ole Torp Lassen, Matthieu Petit

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

A Hidden Markov Model (HMM) is a common statistical model which is widely used for analysis of biological sequence data and other sequential phenomena. In the present paper we show how HMMs can be extended with side-constraints and present constraint solving techniques for efficient inference. Defining HMMs with side-constraints in Constraint Logic Programming has advantages in terms of more compact expression and pruning opportunities during inference. We present a PRISM-based framework for extending HMMs with side-constraints and show how well-known constraints such as cardinality and all_different are integrated. We experimentally validate our approach on the biologically motivated problem of global pairwise alignment.
Original languageEnglish
JournalTheory and Practice of Logic Programming
Volume10
Issue number4-6
Pages (from-to)449-464
Number of pages15
ISSN1471-0684
DOIs
Publication statusPublished - 2010

Keywords

  • Hidden Markov Model with side-constraints
  • inference
  • Programming in statistical modeling

Cite this

Christiansen, Henning ; Have, Christian Theil ; Lassen, Ole Torp ; Petit, Matthieu. / Inference with constrained hidden Markov models in PRISM. In: Theory and Practice of Logic Programming. 2010 ; Vol. 10, No. 4-6. pp. 449-464.
@article{5f69fc808d9111df954c000ea68e967b,
title = "Inference with constrained hidden Markov models in PRISM",
abstract = "A Hidden Markov Model (HMM) is a common statistical model which is widely used for analysis of biological sequence data and other sequential phenomena. In the present paper we show how HMMs can be extended with side-constraints and present constraint solving techniques for efficient inference. Defining HMMs with side-constraints in Constraint Logic Programming has advantages in terms of more compact expression and pruning opportunities during inference. We present a PRISM-based framework for extending HMMs with side-constraints and show how well-known constraints such as cardinality and all_different are integrated. We experimentally validate our approach on the biologically motivated problem of global pairwise alignment.",
keywords = "inferens, Hidden Markov Model with side-constraints, inference, Programming in statistical modeling",
author = "Henning Christiansen and Have, {Christian Theil} and Lassen, {Ole Torp} and Matthieu Petit",
year = "2010",
doi = "10.1017/S1471068410000219",
language = "English",
volume = "10",
pages = "449--464",
journal = "Theory and Practice of Logic Programming",
issn = "1471-0684",
publisher = "Cambridge University Press",
number = "4-6",

}

Inference with constrained hidden Markov models in PRISM. / Christiansen, Henning; Have, Christian Theil; Lassen, Ole Torp; Petit, Matthieu.

In: Theory and Practice of Logic Programming, Vol. 10, No. 4-6, 2010, p. 449-464.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Inference with constrained hidden Markov models in PRISM

AU - Christiansen, Henning

AU - Have, Christian Theil

AU - Lassen, Ole Torp

AU - Petit, Matthieu

PY - 2010

Y1 - 2010

N2 - A Hidden Markov Model (HMM) is a common statistical model which is widely used for analysis of biological sequence data and other sequential phenomena. In the present paper we show how HMMs can be extended with side-constraints and present constraint solving techniques for efficient inference. Defining HMMs with side-constraints in Constraint Logic Programming has advantages in terms of more compact expression and pruning opportunities during inference. We present a PRISM-based framework for extending HMMs with side-constraints and show how well-known constraints such as cardinality and all_different are integrated. We experimentally validate our approach on the biologically motivated problem of global pairwise alignment.

AB - A Hidden Markov Model (HMM) is a common statistical model which is widely used for analysis of biological sequence data and other sequential phenomena. In the present paper we show how HMMs can be extended with side-constraints and present constraint solving techniques for efficient inference. Defining HMMs with side-constraints in Constraint Logic Programming has advantages in terms of more compact expression and pruning opportunities during inference. We present a PRISM-based framework for extending HMMs with side-constraints and show how well-known constraints such as cardinality and all_different are integrated. We experimentally validate our approach on the biologically motivated problem of global pairwise alignment.

KW - inferens

KW - Hidden Markov Model with side-constraints

KW - inference

KW - Programming in statistical modeling

U2 - 10.1017/S1471068410000219

DO - 10.1017/S1471068410000219

M3 - Journal article

VL - 10

SP - 449

EP - 464

JO - Theory and Practice of Logic Programming

JF - Theory and Practice of Logic Programming

SN - 1471-0684

IS - 4-6

ER -