To the top

Page Manager: Webmaster
Last update: 9/11/2012 3:13 PM

Tell a friend about this page
Print version

A Compositional Bayesian … - University of Gothenburg, Sweden Till startsida
To content Read more about how we use cookies on

A Compositional Bayesian Semantics for Natural Language

Conference paper
Authors Jean-Philippe Bernardy
Rasmus Blanck
Stergios Chatzikyriakidis
Shalom Lappin
Published in Proceedings of the First International Workshop on Language Cognition and Computational Models, COLING 2018, August 20, 2018 Santa Fe, New Mexico, USA
ISBN 978-1-948087-57-5
ISSN 1525-2477
Publisher COLING
Publication year 2018
Published at Department of Philosophy, Linguistics and Theory of Science
Language en
Keywords Bayesian models, probabilistic semantics, probabilistic programming languages, Markov Chain Monte Carlo sampling
Subject categories Computational linguistics


We propose a compositional Bayesian semantics that interprets declarative sentences in a natural language by assigning them probability conditions. These are conditional probabilities that estimate the likelihood that a competent speaker would endorse an assertion, given certain hypotheses. Our semantics is implemented in a functional programming language. It estimates the marginal probability of a sentence through Markov Chain Monte Carlo (MCMC) sampling of objects in vector space models satisfying specified hypotheses. We apply our semantics to examples with several predicates and generalised quantifiers, including higher-order quantifiers. It captures the vagueness of predication (both gradable and non-gradable), without positing a precise boundary for classifier application. We present a basic account of semantic learning based on our semantic system. We compare our proposal to other current theories of probabilistic semantics, and we show that it offers several important advantages over these accounts.

Page Manager: Webmaster|Last update: 9/11/2012

The University of Gothenburg uses cookies to provide you with the best possible user experience. By continuing on this website, you approve of our use of cookies.  What are cookies?