%0 Journal Article %1 Ziegner2023-xl %A Ziegner, Fabian %A Borst, Janos %A Niekler, Andreas %A Potthast, Martin %D 2023 %I arXiv %K %T Using language models on low-end hardware %X This paper evaluates the viability of using fixed language models for training text classification networks on low-end hardware. We combine language models with a CNN architecture and put together a comprehensive benchmark with 8 datasets covering single-label and multi-label classification of topic, sentiment, and genre. Our observations are distilled into a list of trade-offs, concluding that there are scenarios, where not fine-tuning a language model yields competitive effectiveness at faster training, requiring only a quarter of the memory compared to fine-tuning.

@article{Ziegner2023-xl, abstract = {This paper evaluates the viability of using fixed language models for training text classification networks on low-end hardware. We combine language models with a CNN architecture and put together a comprehensive benchmark with 8 datasets covering single-label and multi-label classification of topic, sentiment, and genre. Our observations are distilled into a list of trade-offs, concluding that there are scenarios, where not fine-tuning a language model yields competitive effectiveness at faster training, requiring only a quarter of the memory compared to fine-tuning.}, added-at = {2024-09-10T10:41:24.000+0200}, author = {Ziegner, Fabian and Borst, Janos and Niekler, Andreas and Potthast, Martin}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/25b910fec09ee44c4a9e51eb127790ff7/scadsfct}, interhash = {f6242435623e8e3b0f05a5191423c92a}, intrahash = {5b910fec09ee44c4a9e51eb127790ff7}, keywords = {}, publisher = {arXiv}, timestamp = {2024-09-10T10:47:32.000+0200}, title = {Using language models on low-end hardware}, year = 2023 }