Abstract
A “bigger is better” explosion in the number of parameters in deep neural networks has made it increasingly challenging to make state-of-the-art networks accessible in compute-restricted environments. Compression techniques have taken on renewed importance as a way to bridge the gap. However, evaluation of the trade-offs incurred by popular compression techniques has been centered on high-resource datasets. In this work, we instead consider the impact of compression in a data-limited regime. We introduce the term low-resource double bind to refer to the co-occurrence of data limitations and compute resource constraints. This is a common setting for NLP for low-resource languages, yet the trade-offs in performance are poorly studied. Our work offers surprising insights into the relationship between capacity and generalization in data-limited regimes for the task of machine translation. Our experiments on magnitude pruning for translations from English into Yoruba, Hausa, Igbo and German show that in low-resource regimes, sparsity preserves performance on frequent sentences but has a disparate impact on infrequent ones. However, it improves robustness to out-of-distribution shifts, especially for datasets that are very distinct from the training distribution. Our findings suggest that sparsity can play a beneficial role at curbing memorization of low frequency attributes, and therefore offers a promising solution to the low-resource double bind.- Anthology ID:
- 2021.findings-emnlp.282
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2021
- Month:
- November
- Year:
- 2021
- Address:
- Punta Cana, Dominican Republic
- Editors:
- Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
- Venue:
- Findings
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 3316–3333
- Language:
- URL:
- https://aclanthology.org/2021.findings-emnlp.282
- DOI:
- 10.18653/v1/2021.findings-emnlp.282
- Cite (ACL):
- Orevaoghene Ahia, Julia Kreutzer, and Sara Hooker. 2021. The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3316–3333, Punta Cana, Dominican Republic. Association for Computational Linguistics.
- Cite (Informal):
- The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation (Ahia et al., Findings 2021)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/2021.findings-emnlp.282.pdf
- Code
- orevaahia/mc4lrnmt
- Data
- ParaCrawl