Active Curriculum Learning

Borna Jafarpour*, Nicolai Pogrebnyakov, Dawn Sepehr

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

This paper investigates and reveals the relationship between two closely related machine learning disciplines, namely Active Learning (AL) and Curriculum Learning (CL), from the lens of several novel curricula. This paper also introduces Active Curriculum Learning (ACL) which improves AL by combining AL with CL to benefit from the dynamic nature of the AL informativeness concept as well as the human insights used in the design of the curriculum heuristics. Comparison of the performance of ACL and AL on two public datasets for the Named Entity Recognition (NER) task shows the effectiveness of combining AL and CL using our proposed framework.
Original languageEnglish
Title of host publicationInterNLP 2021. First Workshop on Interactive Learning for Natural Language Processing : Proceedings of the Workshop
Number of pages6
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics
Publication date2021
Pages40-45
ISBN (Print)9781954085664
Publication statusPublished - 2021
EventFirst Workshop on Interactive Learning for Natural Language Processing. InterNLP 2021: Workshop at ACL 2021 - Virtual Conference
Duration: 5 Aug 20215 Aug 2021
Conference number: 1
https://sites.google.com/view/internlp2021/home

Workshop

WorkshopFirst Workshop on Interactive Learning for Natural Language Processing. InterNLP 2021
Number1
LocationVirtual Conference
Period05/08/202105/08/2021
Internet address

Cite this