Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance.
Gee, L., Zugarini, A., Rigutini, L., Torroni, P. (2022). Fast Vocabulary Transfer for Language Model Compression. Association for Computational Linguistics [10.18653/v1/2022.emnlp-industry.41].
Fast Vocabulary Transfer for Language Model Compression
Torroni P.
2022
Abstract
Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
