lrtc

Active Learning for BERT: An Empirical Study. Real world scenarios present a challenge for text classification, since labels are usually expensive and the data is often characterized by class imbalance. Active Learning (AL) is a ubiquitous paradigm to cope with data scarcity. Recently, pre-trained NLP models, and BERT in particular, are receiving massive attention due to their outstanding performance in various NLP tasks. However, the use of AL with deep pre-trained models has so far received little consideration. Here, we present a large-scale empirical study on active learning techniques for BERT-based classification, addressing a diverse set of AL strategies and datasets. We focus on practical scenarios of binary text classification, where the annotation budget is very small, and the data is often skewed. Our results demonstrate that AL can boost BERT performance, especially in the most realistic scenario in which the initial set of labeled examples is created using keyword-based queries, resulting in a biased sample of the minority class. We release our research framework, aiming to facilitate future research along the lines explored here

Keywords for this software

Anything in here will be replaced on browsers that support the canvas element


References in zbMATH (referenced in 1 article )

Showing result 1 of 1.
Sorted by year (citations)

  1. Christopher Schröder, Lydia Müller, Andreas Niekler, Martin Potthast: Small-text: Active Learning for Text Classification in Python (2021) arXiv