Active Curriculum Learning

Borna Jafarpour*, Nicolai Pogrebnyakov, Dawn Sepehr

*Corresponding author af dette arbejde

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningpeer review

Abstrakt

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.
OriginalsprogEngelsk
TitelInterNLP 2021. First Workshop on Interactive Learning for Natural Language Processing : Proceedings of the Workshop
Antal sider6
UdgivelsesstedStroudsburg, PA
ForlagAssociation for Computational Linguistics
Publikationsdato2021
Sider40-45
ISBN (Trykt)9781954085664
StatusUdgivet - 2021
BegivenhedFirst Workshop on Interactive Learning for Natural Language Processing. InterNLP 2021: Workshop at ACL 2021 - Virtual Conference
Varighed: 5 aug. 20215 aug. 2021
Konferencens nummer: 1
https://sites.google.com/view/internlp2021/home

Workshop

WorkshopFirst Workshop on Interactive Learning for Natural Language Processing. InterNLP 2021
Nummer1
LokationVirtual Conference
Periode05/08/202105/08/2021
Internetadresse

Citationsformater