TADA: Task-Agnostic Dialect Adapters for English
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F23%3A6H5GJ2U8" target="_blank" >RIV/00216208:11320/23:6H5GJ2U8 - isvavai.cz</a>
Result on the web
<a href="http://arxiv.org/abs/2305.16651" target="_blank" >http://arxiv.org/abs/2305.16651</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2023.findings-acl.51" target="_blank" >10.18653/v1/2023.findings-acl.51</a>
Alternative languages
Result language
angličtina
Original language name
TADA: Task-Agnostic Dialect Adapters for English
Original language description
"Large Language Models, the dominant starting point for Natural Language Processing (NLP) applications, fail at a higher rate for speakers of English dialects other than Standard American English (SAE). Prior work addresses this using task-specific data or synthetic data augmentation, both of which require intervention for each dialect and task pair. This poses a scalability issue that prevents the broad adoption of robust dialectal English NLP. We introduce a simple yet effective method for task-agnostic dialect adaptation by aligning non-SAE dialects using adapters and composing them with task-specific adapters from SAE. Task-Agnostic Dialect Adapters (TADA) improve dialectal robustness on 4 dialectal variants of the GLUE benchmark without task-specific supervision."
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: ACL 2023"
ISBN
978-1-959429-62-3
ISSN
—
e-ISSN
—
Number of pages
12
Pages from-to
813-824
Publisher name
ACL
Place of publication
—
Event location
Singapore
Event date
Jan 1, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—