Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-30985
Title: | On the Need of Cross Validation for Discourse Relation Classification |
Author(s): | Shi, Wei Demberg, Vera |
Editor(s): | Kunnemann, Florian Iñurrieta, Uxoa Camilleri, John J. Coll Ardanuy, Mariona |
Language: | English |
Title: | European Chapter of the Association for Computational Linguistics - proceedings of the Student Research Workshop : April 3-7, 2017 : EACL 2017 |
Startpage: | 150 |
Endpage: | 156 |
Publisher/Platform: | ACL |
Year of Publication: | 2017 |
Place of publication: | Stroudsburg, PA |
Title of the Conference: | EACL 2017 |
Place of the conference: | Valencia, Spain |
Publikation type: | Conference Paper |
Abstract: | The task of implicit discourse relation classification has received increased attention in recent years, including two CoNNL shared tasks on the topic. Existing machine learning models for the task train on sections 2-21 of the PDTB and test on section 23, which includes a total of 761 implicit discourse relations. In this paper, we’d like to make a methodological point, arguing that the standard test set is too small to draw conclusions about whether the inclusion of certain features constitute a genuine improvement, or whether one got lucky with some properties of the test set, and argue for the adoption of cross validation for the discourse relation classification task by the community. |
DOI of the first publication: | 10.18653/v1/E17-2024 |
URL of the first publication: | https://www.aclweb.org/anthology/E17-2024/ |
Link to this record: | hdl:20.500.11880/29702 http://dx.doi.org/10.22028/D291-30985 |
ISBN: | 978-1-945626-37-1 |
Date of registration: | 23-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.