Please use this identifier to cite or link to this item: doi:10.22028/D291-30968
Volltext verfügbar? / Dokumentlieferung
Title: Toward Bayesian Synchronous Tree Substitution Grammars for Sentence Planning
Author(s): Howcroft, David M.
Klakow, Dietrich
Demberg, Vera
Editor(s): Krahmer, Emiel
Language: English
Title: The 11th International Natural Language Generation conference - proceedings of the conference : November 5-8, 2018, Tilburg, The Netherlands : INLG 2018
Startpage: 391
Endpage: 396
Publisher/Platform: ACL
Year of Publication: 2018
Place of publication: Stroudsburg, PA
Title of the Conference: INLG 2018
Place of the conference: Tilburg, The Netherlands
Publikation type: Conference Paper
Abstract: Developing conventional natural language generation systems requires extensive attention from human experts in order to craft complex sets of sentence planning rules. We propose a Bayesian nonparametric approach to learn sentence planning rules by inducing synchronous tree substitution grammars for pairs of text plans and morphosyntactically-specified dependency trees. Our system is able to learn rules which can be used to generate novel texts after training on small datasets.
DOI of the first publication: 10.18653/v1/W18-6546
URL of the first publication:
Link to this record: hdl:20.500.11880/29696
ISBN: 978-1-948087-86-5
Date of registration: 22-Sep-2020
Faculty: MI - Fakultät für Mathematik und Informatik
Department: MI - Informatik
Professorship: MI - Prof. Dr. Vera Demberg
Collections:SciDok - Der Wissenschaftsserver der Universität des Saarlandes

Files for this record:
There are no files associated with this item.

Items in SciDok are protected by copyright, with all rights reserved, unless otherwise indicated.