{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/the-low-resource-double-bind-an-empirical","title":"The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translation","arxiv_id":"2110.03036","date":"2021-10-06","proceeding":"Findings (EMNLP) 2021 11","authors":["Orevaoghene Ahia","Julia Kreutzer","Sara Hooker"],"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.","url_abs":"https://arxiv.org/abs/2110.03036v1","url_pdf":"https://arxiv.org/pdf/2110.03036v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"the-low-resource-double-bind-an-empirical","repo_url":"https://github.com/orevaahia/mc4lrnmt","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"memorization","task_name":"Memorization"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.03036","atlas_url":"https://app.syntology.ai/?focus=2110.03036","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}