English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Active learning has been shown to be an effective way to alleviate some ofthe effort required in utilising large collections of unlabelled data formachine learning tasks without needing to fully label them. The representationmechanism used to represent text documents when performing active learning,however, has a significant influence on how effective the process will be.While simple vector representations such as bag-of-words and embedding-basedrepresentations based on techniques such as word2vec have been shown to be aneffective way to represent documents during active learning, the emergence ofrepresentation mechanisms based on the pre-trained transformer-based neuralnetwork models popular in natural language processing research (e.g. BERT)offer a promising, and as yet not fully explored, alternative. This paperdescribes a comprehensive evaluation of the effectiveness of representationsbased on pre-trained transformer-based language models for active learning.This evaluation shows that transformer-based models, especially BERT-likemodels, that have not yet been widely used in active learning, achieve asignificant improvement over more commonly used vector representations likebag-of-words or other classical word embeddings like word2vec. This paper alsoinvestigates the effectiveness of representations based on variants of BERTsuch as Roberta, Albert as well as comparing the effectiveness of the [CLS]token representation and the aggregated representation that can be generatedusing BERT-like models. Finally, we propose an approach Adaptive Tuning ActiveLearning. Our experiments show that the limited label information acquired inactive learning can not only be used for training a classifier but can alsoadaptively improve the embeddings generated by the BERT-like language models aswell.

Investigating the Effectiveness of Representations Based on Pretrained  Transformer-based Language Models in Active Learning for Labelling Text  Datasets