Joint End-to-end Semantic Proto-role Labeling
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3ANE6IVPPZ" target="_blank" >RIV/00216208:11320/23:NE6IVPPZ - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2023.acl-short.63/" target="_blank" >https://aclanthology.org/2023.acl-short.63/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2023.acl-short.63" target="_blank" >10.18653/v1/2023.acl-short.63</a>
Alternative languages
Result language
angličtina
Original language name
Joint End-to-end Semantic Proto-role Labeling
Original language description
"Semantic proto-role labeling (SPRL) assigns properties to arguments based on a series of binary labels. While multiple studies have evaluated various approaches to SPRL, it has only been studied in-depth as a standalone task using gold predicate/argument pairs. How do SPRL systems perform as part of an information extraction pipeline? We model SPRL jointly with predicate-argument extraction using a deep transformer model. We find that proto-role labeling is surprisingly robust in this setting, with only a small decrease when using predicted arguments. We include a detailed analysis of each component of the joint system, and an error analysis to understand correlations in errors between system stages. Finally, we study the effects of annotation errors on SPRL."
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
—
Continuities
—
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)"
ISBN
978-1-959429-71-5
ISSN
—
e-ISSN
—
Number of pages
14
Pages from-to
723-736
Publisher name
ACL
Place of publication
Toronto, Canada
Event location
Toronto, Canada
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—