Please use this identifier to cite or link to this item:
Volltext verfügbar? / Dokumentlieferung
doi:10.22028/D291-38633
Title: | Comparison of methods for explicit discourse connective identification across various domains |
Author(s): | Scholman, Merel Cleo Johanna Dong, Tianai Yung, Frances Pikyu 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: | 95-106 |
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: | Existing parse methods use varying approaches to identify explicit discourse connectives, but their performance has not been consistently evaluated in comparison to each other, nor have they been evaluated consistently on text other than newspaper articles. We here assess the performance on explicit connective identification of three parse methods (PDTB e2e, Lin et al., 2014; the winner of CONLL2015, Wang et al., 2015; and DisSent, Nie et al., 2019), along with a simple heuristic. We also examine how well these systems generalize to different datasets, namely written newspaper text (PDTB), written scientific text (BioDRB), prepared spoken text (TED-MDB) and spontaneous spoken text (Disco-SPICE). The results show that the e2e parser outperforms the other parse methods in all datasets. However, performance drops significantly from the PDTB to all other datasets. We provide a more fine-grained analysis of domain differences and connectives that prove difficult to parse, in order to highlight the areas where gains can be made. |
DOI of the first publication: | 10.18653/v1/2021.codi-main.9 |
Link to this record: | urn:nbn:de:bsz:291--ds-386339 hdl:20.500.11880/34829 http://dx.doi.org/10.22028/D291-38633 |
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.