Konferensartikel

Predicates as Boxes in Bayesian Semantics for Natural Language

Jean-Philippe Bernardy
Department of philosophy, linguistics and theory of science, Centre for linguistics and studies in probability, Gothenburg Univeristy, Sweden

Rasmus Blanck
Department of philosophy, linguistics and theory of science, Centre for linguistics and studies in probability, Gothenburg Univeristy, Sweden

Stergios Chatzikyriakidis
Department of philosophy, linguistics and theory of science, Centre for linguistics and studies in probability, Gothenburg Univeristy, Sweden

Shalom Lappin
Department of philosophy, linguistics and theory of science, Centre for linguistics and studies in probability, Gothenburg Univeristy, Sweden

Aleksandre Maskharashvili
Department of philosophy, linguistics and theory of science, Centre for linguistics and studies in probability, Gothenburg Univeristy, Sweden

Ladda ner artikel

Ingår i: Proceedings of the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa), September 30 - October 2, Turku, Finland

Linköping Electronic Conference Proceedings 167:37, s. 333--337

NEALT Proceedings Series 42:37, s. 333--337

Visa mer +

Publicerad: 2019-10-02

ISBN: 978-91-7929-995-8

ISSN: 1650-3686 (tryckt), 1650-3740 (online)

Abstract

In this paper, we present a Bayesian approach to natural language semantics. Our main focus is on the inference task in an environment where judgments require probabilistic reasoning. We treat nouns, verbs, adjectives, etc. as unary predicates, and we model them as boxes in a bounded domain. We apply Bayesian learning to satisfy constraints expressed as premises. In this way we construct a model, by specifying boxes for the predicates. The probability of the hypothesis (the conclusion) is evaluated against the model that incorporates the premises as constraints.

Nyckelord

Bayesian models probabilistic semantics generalised quantifiers vague predicates compositionality Inference

Referenser

Inga referenser tillgängliga

Citeringar i Crossref