Evidence > Intuition: Transferability Estimation for Encoder Selection

Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review


With the increase in availability of large pre-trained language models (LMs) in Natural Language Processing (NLP), it becomes critical to assess their fit for a specific target task a priori—as fine-tuning the entire space of available LMs is computationally prohibitive and unsustainable. However, encoder transferability estimation has received little to no attention in NLP. In this paper, we propose to generate quantitative evidence to predict which LM, out of a pool of models, will perform best on a target task without having to fine-tune all candidates. We provide a comprehensive study on LM ranking for 10 NLP tasks spanning
the two fundamental problem types of classification and structured prediction. We adopt the state-of-the-art Logarithm of Maximum Evidence (LogME) measure from Computer Vision (CV) and find that it positively correlates with final LM performance in 94% of the setups. In the first study of its kind, we further compare transferability measures with the de facto standard of human practitioner ranking, finding that evidence from quantitative metrics is more robust than pure intuition and can help identify unexpected LM candidates.
TitelThe 2022 Conference on Empirical Methods in Natural Language Processing : EMNLP 2022
UdgivelsesstedAbu Dhabi, United Arab Emirates
ForlagAssociation for Computational Linguistics
Publikationsdato7 dec. 2022
StatusUdgivet - 7 dec. 2022


Dyk ned i forskningsemnerne om 'Evidence > Intuition: Transferability Estimation for Encoder Selection'. Sammen danner de et unikt fingeraftryk.