Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networks

1 code implementation • NeurIPS 2021 • Robert Lieck, Martin Rohrmeier

While PCFGs allow for nested hierarchical dependencies (tree structures), their latent variables (non-terminal symbols) have to be discrete.

Bayesian Inference Change Point Detection

Formal models of Structure Building in Music, Language and Animal Songs

no code implementations • 16 Jan 2019 • Willem Zuidema, Dieuwke Hupkes, Geraint Wiggins, Constance Scharff, Martin Rohrmeier

Human language, music and a variety of animal vocalisations constitute ways of sonic communication that exhibit remarkable structural complexity.

A generalized parsing framework for Abstract Grammars

no code implementations • 31 Oct 2017 • Daniel Harasim, Chris Bruno, Eva Portelance, Martin Rohrmeier, Timothy J. O'Donnell

This technical report presents a general framework for parsing a variety of grammar formalisms.