Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A4B2M8CT5" target="_blank" >RIV/00216208:11320/23:4B2M8CT5 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2023.findings-eacl.44/" target="_blank" >https://aclanthology.org/2023.findings-eacl.44/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2023.findings-eacl.44" target="_blank" >10.18653/v1/2023.findings-eacl.44</a>
Alternative languages
Result language
angličtina
Original language name
Zero-shot Transfer of Article-aware Legal Outcome Classification for European Court of Human Rights Cases
Original language description
"In this paper, we cast Legal Judgment Prediction on European Court of Human Rights cases into an article-aware classification task, where the case outcome is classified from a combined input of case facts and convention articles. This configuration facilitates the model learning some legal reasoning ability in mapping article text to specific case fact text. It also provides an opportunity to evaluate the model’s ability to generalize to zero-shot settings when asked to classify the case outcome with respect to articles not seen during training. We devise zero-shot experiments and apply domain adaptation methods based on domain discrimination and Wasserstein distance. Our results demonstrate that the article-aware architecture outperforms straightforward fact classification. We also find that domain adaptation methods improve zero-shot transfer performance, with article relatedness and encoder pre-training influencing the effect."
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
"Findings of the Association for Computational Linguistics: EACL 2023"
ISBN
978-1-959429-47-0
ISSN
—
e-ISSN
—
Number of pages
13
Pages from-to
605-617
Publisher name
ACL
Place of publication
Dubrovnik, Croatia
Event location
Dubrovnik, Croatia
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—