$C^3$: Confidence Calibration Model Cascade for Inference-Efficient Cross-Lingual Natural Language Understanding

arXiv:2402.15991v1 Announce Type: new
Abstract: Cross-lingual natural language understanding (NLU) is a critical task in natural language processing (NLP). Recent advancements have seen multilingual pre-trained language models (mPLMs) significantly enhance the performance of these tasks. However, mPLMs necessitate substantial resources and incur high computational costs during inference, posing challenges for deployment in real-world and real-time systems. Existing model cascade methods seek to enhance inference efficiency by greedily selecting the lightest model capable of processing the current input from a variety …

abstract arxiv challenges computational confidence costs cross-lingual cs.cl inference language language models language processing language understanding multilingual natural natural language natural language processing nlp nlu performance processing resources tasks type understanding