Predicates as Boxes in Bayesian Semantics for Natural Language

Jean-Philippe Bernardy; Rasmus Blanck; Stergios Chatzikyriakidis; Shalom Lappin; Aleksandre Maskharashvili

Predicates as Boxes in Bayesian Semantics for Natural Language

Jean-Philippe Bernardy, Rasmus Blanck, Stergios Chatzikyriakidis, Shalom Lappin, Aleksandre Maskharashvili

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English (US)
Title of host publication	Proceedings of the 22nd Nordic Conference on Computational Linguistics
Editors	Mareike Hartmann, Barbara Plank
Place of Publication	Turku
Publisher	Linköping University Electronic Press
Pages	333-337
Number of pages	5
State	Published - Sep 2019
Externally published	Yes

Online availability

https://aclanthology.org/W19-6137

Library availability

Discover UIUC Full Text

Cite this

Predicates as Boxes in Bayesian Semantics for Natural Language. / Bernardy, Jean-Philippe; Blanck, Rasmus; Chatzikyriakidis, Stergios et al.
Proceedings of the 22nd Nordic Conference on Computational Linguistics. ed. / Mareike Hartmann; Barbara Plank. Turku: Linköping University Electronic Press, 2019. p. 333-337.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

@inproceedings{4f882bd616244cd28abaaa477739c7d8,

title = "Predicates as Boxes in Bayesian Semantics for Natural Language",

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.",

author = "Jean-Philippe Bernardy and Rasmus Blanck and Stergios Chatzikyriakidis and Shalom Lappin and Aleksandre Maskharashvili",

year = "2019",

month = sep,

language = "English (US)",

pages = "333--337",

editor = "Mareike Hartmann and Barbara Plank",

booktitle = "Proceedings of the 22nd Nordic Conference on Computational Linguistics",

publisher = "Link{\"o}ping University Electronic Press",

}

TY - GEN

T1 - Predicates as Boxes in Bayesian Semantics for Natural Language

AU - Bernardy, Jean-Philippe

AU - Blanck, Rasmus

AU - Chatzikyriakidis, Stergios

AU - Lappin, Shalom

AU - Maskharashvili, Aleksandre

PY - 2019/9

Y1 - 2019/9

N2 - 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.

AB - 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.

M3 - Conference contribution

SP - 333

EP - 337

BT - Proceedings of the 22nd Nordic Conference on Computational Linguistics

A2 - Hartmann, Mareike

A2 - Plank, Barbara

PB - Linköping University Electronic Press

CY - Turku

ER -

Predicates as Boxes in Bayesian Semantics for Natural Language

Abstract

Online availability

Library availability

Fingerprint

Cite this