2016/09/08 by Shanbo Chu, Yong Jiang, Chu, Shanbo +3 · 2 citations
Computer Science · Mathematics · #Artificial Intelligence (cs.AI) #Artificial intelligence #Bayesian Modeling and Causal Inference #Computer science #Context (archaeology) #Dependency (UML) #FOS: Computer and information sciences #Independence (probability theory) #Latent variable #Machine learning #Mathematics #Natural Language Processing Techniques #Probabilistic logic #Statistics #Topic Modeling #cs.AI
paper · pdf · doi:10.48550/arxiv.1609.02236
published in arXiv (Cornell University) (Cornell University) · 10 pages, 3 figures, conference
openalex publication_date 2016/09/08 · arxiv created 2016/11/20 · arxiv updated 2016/11/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08
Probabilistic modeling is one of the foundations of modern machine learning and artificial intelligence. In this paper, we propose a novel type of probabilistic models named latent dependency forest models (LDFMs). A LDFM models the dependencies between random variables with a forest structure that can change dynamically based on the variable values. It is therefore capable of modeling context-specific independence. We parameterize a LDFM using a first-order non-projective dependency grammar. Learning LDFMs from data can be formulated purely as a parameter learning problem, and hence the difficult problem of model structure learning is circumvented. Our experimental results show that LDFMs are competitive with existing probabilistic models.