Soft Alignment Objectives for Robust Adaptation of Language Generation

Varování

Publikace nespadá pod Ekonomicko-správní fakultu, ale pod Fakultu informatiky. Oficiální stránka publikace je na webu muni.cz.
Autoři

ŠTEFÁNIK Michal KADLČÍK Marek SOJKA Petr

Rok publikování 2023
Druh Článek ve sborníku
Konference Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www https://aclanthology.org/2023.acl-long.492
Doi http://dx.doi.org/10.18653/v1/2023.acl-long.492
Klíčová slova generation; robustness; machine translation; adaptation
Popis 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.
Související projekty:

Používáte starou verzi internetového prohlížeče. Doporučujeme aktualizovat Váš prohlížeč na nejnovější verzi.