Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-30968
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: | https://www.aclweb.org/anthology/W18-6546/ |
Link to this record: | hdl:20.500.11880/29696 http://dx.doi.org/10.22028/D291-30968 |
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.