Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F21%3A10442301" target="_blank" >RIV/00216208:11320/21:10442301 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Unifying Cross-Lingual Semantic Role Labeling with Heterogeneous Linguistic Resources
Original language description
While cross-lingual techniques are finding increasing success in a wide range of Natural Language Processing tasks, their application to Semantic Role Labeling (SRL) has been strongly limited by the fact that each language adopts its own linguistic formalism, from PropBank for English to AnCora for Spanish and PDT-Vallex for Czech, inter alia. In this work, we address this issue and present a unified model to perform cross-lingual SRL over heterogeneous linguistic resources. Our model implicitly learns a high-quality mapping for different formalisms across diverse languages without resorting to word alignment and/or translation techniques. We find that, not only is our cross-lingual system competitive with the current state of the art but that it is also robust to low-data scenarios. Most interestingly, our unified model is able to annotate a sentence in a single forward pass with all the inventories it was trained with, providing a tool for the analysis and comparison of linguistic theories across different languages. We release our code and model at https://github.com/SapienzaNLP/unify-srl.
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
2021
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 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
ISBN
978-1-954085-46-6
ISSN
—
e-ISSN
—
Number of pages
14
Pages from-to
338-351
Publisher name
Association for Computational Linguistics
Place of publication
Stroudsburg
Event location
online
Event date
Jun 6, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—