Other formats:
BibTeX
LaTeX
RIS
@inproceedings{2288099,
author = {Štefánik, Michal and Kadlčík, Marek and Sojka, Petr},
address = {Toronto, Canada},
booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
doi = {http://dx.doi.org/10.18653/v1/2023.acl-long.492},
keywords = {generation; robustness; machine translation; adaptation},
howpublished = {elektronická verze "online"},
language = {eng},
location = {Toronto, Canada},
isbn = {978-1-959429-72-2},
note = {To appear},
pages = {8837-8853},
publisher = {Association for Computational Linguistics},
title = {Soft Alignment Objectives for Robust Adaptation of Language Generation},
url = {https://aclanthology.org/2023.acl-long.492},
year = {2023}
}
TY - JOUR
ID - 2288099
AU - Štefánik, Michal - Kadlčík, Marek - Sojka, Petr
PY - 2023
TI - Soft Alignment Objectives for Robust Adaptation of Language Generation
PB - Association for Computational Linguistics
CY - Toronto, Canada
SN - 9781959429722
N1 - To appear
KW - generation
KW - robustness
KW - machine translation
KW - adaptation
UR - https://aclanthology.org/2023.acl-long.492
N2 - Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model's ability to generalize to other domains, making the open-ended deployments of the adapted models prone to errors. This work introduces novel training objectives built upon a semantic similarity of the predicted tokens to the reference. Our results show that (1) avoiding the common assumption of a single correct prediction by constructing the training target from tokens' semantic similarity can largely mitigate catastrophic forgetting of adaptation, while (2) preserving the adaptation in-domain quality, (3) with negligible additions to compute costs. In the broader context, the objectives grounded in a continuous token similarity pioneer the exploration of the middle ground between the efficient but na\"{\i}ve exact-match token-level objectives and expressive but computationally- and resource-intensive sequential objectives.
ER -
ŠTEFÁNIK, Michal, Marek KADLČÍK and Petr SOJKA. Soft Alignment Objectives for Robust Adaptation of Language Generation. Online. In \textit{Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}. Toronto, Canada: Association for Computational Linguistics, 2023, p.~8837-8853. ISBN~978-1-959429-72-2. Available from: https://dx.doi.org/10.18653/v1/2023.acl-long.492.
|
