AdaptOr: Objective-Centric Adaptation Framework for Language Models
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14330%2F22%3A00125674" target="_blank" >RIV/00216224:14330/22:00125674 - isvavai.cz</a>
Result on the web
<a href="https://aclanthology.org/2022.acl-demo.26/" target="_blank" >https://aclanthology.org/2022.acl-demo.26/</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2022.acl-demo.26" target="_blank" >10.18653/v1/2022.acl-demo.26</a>
Alternative languages
Result language
angličtina
Original language name
AdaptOr: Objective-Centric Adaptation Framework for Language Models
Original language description
Progress in natural language processing research is catalyzed by the possibilities given by the widespread software frameworks. This paper introduces the Adaptor library that transposes the traditional model-centric approach composed of pre-training + fine-tuning steps to the objective-centric approach, composing the training process by applications of selected objectives. We survey research directions that can benefit from enhanced objective-centric experimentation in multitask training, custom objectives development, dynamic training curricula, or domain adaptation. Adaptor aims to ease the reproducibility of these research directions in practice. Finally, we demonstrate the practical applicability of Adaptor in selected unsupervised domain adaptation scenarios.
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
S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Others
Publication year
2022
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 60th Conference of Association of Computational Linguistics, ACL 2022
ISBN
9781955917247
ISSN
0736-587X
e-ISSN
—
Number of pages
9
Pages from-to
261-269
Publisher name
Association for Computational Linguistics, ACL
Place of publication
Dublin, Irsko
Event location
Dublin, Irsko
Event date
Jan 1, 2022
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—