Active Curriculum Learning

Borna Jafarpour, Dawn Sepehr, Nick Pogrebnyakov


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.
Anthology ID:
2021.internlp-1.6
Volume:
Proceedings of the First Workshop on Interactive Learning for Natural Language Processing
Month:
August
Year:
2021
Address:
Online
Editors:
Kianté Brantley, Soham Dan, Iryna Gurevych, Ji-Ung Lee, Filip Radlinski, Hinrich Schütze, Edwin Simpson, Lili Yu
Venue:
InterNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
40–45
Language:
URL:
https://aclanthology.org/2021.internlp-1.6
DOI:
10.18653/v1/2021.internlp-1.6
Bibkey:
Cite (ACL):
Borna Jafarpour, Dawn Sepehr, and Nick Pogrebnyakov. 2021. Active Curriculum Learning. In Proceedings of the First Workshop on Interactive Learning for Natural Language Processing, pages 40–45, Online. Association for Computational Linguistics.
Cite (Informal):
Active Curriculum Learning (Jafarpour et al., InterNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.internlp-1.6.pdf