Enregistré dans:
Détails bibliographiques
Auteurs principaux: Hościłowicz, Jakub, Sowański, Marcin, Czubowski, Piotr, Janicki, Artur
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2301.11688
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910645642854400
author Hościłowicz, Jakub
Sowański, Marcin
Czubowski, Piotr
Janicki, Artur
author_facet Hościłowicz, Jakub
Sowański, Marcin
Czubowski, Piotr
Janicki, Artur
contents In this article, we use probing to investigate phenomena that occur during fine-tuning and knowledge distillation of a BERT-based natural language understanding (NLU) model. Our ultimate purpose was to use probing to better understand practical production problems and consequently to build better NLU models. We designed experiments to see how fine-tuning changes the linguistic capabilities of BERT, what the optimal size of the fine-tuning dataset is, and what amount of information is contained in a distilled NLU based on a tiny Transformer. The results of the experiments show that the probing paradigm in its current form is not well suited to answer such questions. Structural, Edge and Conditional probes do not take into account how easy it is to decode probed information. Consequently, we conclude that quantification of information decodability is critical for many practical applications of the probing paradigm.
format Preprint
id arxiv_https___arxiv_org_abs_2301_11688
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?
Hościłowicz, Jakub
Sowański, Marcin
Czubowski, Piotr
Janicki, Artur
Computation and Language
Machine Learning
In this article, we use probing to investigate phenomena that occur during fine-tuning and knowledge distillation of a BERT-based natural language understanding (NLU) model. Our ultimate purpose was to use probing to better understand practical production problems and consequently to build better NLU models. We designed experiments to see how fine-tuning changes the linguistic capabilities of BERT, what the optimal size of the fine-tuning dataset is, and what amount of information is contained in a distilled NLU based on a tiny Transformer. The results of the experiments show that the probing paradigm in its current form is not well suited to answer such questions. Structural, Edge and Conditional probes do not take into account how easy it is to decode probed information. Consequently, we conclude that quantification of information decodability is critical for many practical applications of the probing paradigm.
title Can We Use Probing to Better Understand Fine-tuning and Knowledge Distillation of the BERT NLU?
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2301.11688