Towards Domain Robustness of Neural Language Models

Varování

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

ŠTEFÁNIK Michal SOJKA Petr

Rok publikování 2021
Druh Článek ve sborníku
Konference Recent Advances in Slavonic Natural Language Processing (RASLAN 2021)
Fakulta / Pracoviště MU

Fakulta informatiky

Citace
www
Klíčová slova Generalization; Debiasing; Domain extrapolation; Domain adaptation; Domain robustness; Neural language models
Popis This work summarises recent progress in generalization evaluation and training of deep neural networks, categorized in data-centric and model-centric overviews. Grounded in the results of the referenced work, we propose three future directions towards reaching higher robustness of language models to an unknown domain or its adaptation to an existing domain of interest. In the example propositions that practically complement each of the directions, we introduce novel ideas of a) dynamic objective selection, b) language modeling respecting the token similarities to the ground truth and c) a framework of additive component of the loss utilizing the well-performing generalization measures.
Související projekty:

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