Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU

Fenia Christopoulou, Gerasimos Lampouras, Ignacio Iacobacci


Abstract
Curriculum Learning (CL) is a technique of training models via ranking examples in a typically increasing difficulty trend with the aim of accelerating convergence and improving generalisability. Current approaches for Natural Language Understanding (NLU) tasks use CL to improve in-distribution data performance often via heuristic-oriented or task-agnostic difficulties. In this work, instead, we employ CL for NLU by taking advantage of training dynamics as difficulty metrics, i.e., statistics that measure the behavior of the model at hand on specific task-data instances during training and propose modifications of existing CL schedulers based on these statistics. Differently from existing works, we focus on evaluating models on in-distribution (ID), out-of-distribution (OOD) as well as zero-shot (ZS) cross-lingual transfer datasets. We show across several NLU tasks that CL with training dynamics can result in better performance mostly on zero-shot cross-lingual transfer and OOD settings with improvements up by 8.5% in certain cases. Overall, experiments indicate that training dynamics can lead to better performing models with smoother training compared to other difficulty metrics while being 20% faster on average. In addition, through analysis we shed light on the correlations of task-specific versus task-agnostic metrics.
Anthology ID:
2022.emnlp-main.167
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2595–2611
Language:
URL:
https://aclanthology.org/2022.emnlp-main.167
DOI:
10.18653/v1/2022.emnlp-main.167
Bibkey:
Cite (ACL):
Fenia Christopoulou, Gerasimos Lampouras, and Ignacio Iacobacci. 2022. Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2595–2611, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLU (Christopoulou et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.167.pdf