Please use this identifier to cite or link to this item: doi:10.22028/D291-38632
Volltext verfügbar? / Dokumentlieferung
Title: A practical perspective on connective generation
Author(s): Yung, Frances Pikyu
Scholman, Merel Cleo Johanna
Demberg, Vera
Editor(s): Zeldes, Amir
Language: English
Title: The Shared Task on Discourse Relation Parsing and Treebanking - proceedings of the 2nd Shared Task on Discourse Relation Parsing and Treebanking (DISRPT 2021) : November 11, 2021, Punta Cana, Dominican Republic : EMNLP 2021
Pages: 72-83
Publisher/Platform: ACL
Year of Publication: 2021
Place of publication: Stroudsburg, PA
Place of the conference: Punta Cana, Dominican Republic
DDC notations: 004 Computer science, internet
Publikation type: Conference Paper
Abstract: In data-driven natural language generation, we typically know what relation should be expressed and need to select a connective to lexicalize it. In the current contribution, we analyse whether a sophisticated connective generation module is necessary to select a connective, or whether this can be solved with simple methods (such as random choice between connectives that are known to express a given relation, or usage of a generic language model). Comparing these methods to the distributions of connective choices from a human connective insertion task, we find mixed results: for some relations, it is acceptable to lexicalize them using any of the connectives that mark this relation. However, for other relations (temporals, concessives) either a more detailed relation distinction needs to be introduced, or a more sophisticated connective choice module would be necessary.
DOI of the first publication: 10.18653/v1/2021.codi-main.7
Link to this record: urn:nbn:de:bsz:291--ds-386326
ISBN: 978-1-955917-13-1
Date of registration: 2-Jan-2023
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.