← Application Areas
Machine Learning › Application Areas ›

Model Compression

1503 directly classified papers

Papers per year

Papers

What Do Compressed Multilingual Machine Translation Models Forget? EMNLP 2022
MockingBERT: A Method for Retroactively Adding Resilience to NLP Models COLING 2022
MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation NAACL 2022
KroneckerBERT: Significant Compression of Pre-trained Language Models Through Kronecker Decomposition and Knowledge Distillation NAACL 2022
Too Brittle to Touch: Comparing the Stability of Quantization and Distillation towards Developing Low-Resource MT Models EMNLP 2022
Sparse Teachers Can Be Dense with Knowledge EMNLP 2022
An Effective Post-training Embedding Binarization Approach for Fast Online Top-K Passage Matching IJCNLP 2022
PAC-Net: A Model Pruning Approach to Inductive Transfer Learning ICML 2022
Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model EMNLP 2022
Hypoformer: Hybrid Decomposition Transformer for Edge-friendly Neural Machine Translation EMNLP 2022
Improving Machine Translation with Phrase Pair Injection and Corpus Filtering EMNLP 2022
The Importance of Being Parameters: An Intra-Distillation Method for Serious Gains EMNLP 2022
COST-EFF: Collaborative Optimization of Spatial and Temporal Efficiency with Slenderized Multi-exit Language Models EMNLP 2022
Model Cascading: Towards Jointly Improving Efficiency and Accuracy of NLP Systems EMNLP 2022
Zero-Shot Dynamic Quantization for Transformer Inference EMNLP 2022
Investigating Ensemble Methods for Model Robustness Improvement of Text Classifiers EMNLP 2022
RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise EMNLP 2022
SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters EMNLP 2022
Partially-Random Initialization: A Smoking Gun for Binarization Hypothesis of BERT EMNLP 2022
PALT: Parameter-Lite Transfer of Language Models for Knowledge Graph Completion EMNLP 2022
Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization EMNLP 2022
Parameter-Efficient Legal Domain Adaptation EMNLP 2022
Forward Compatible Training for Large-Scale Embedding Retrieval Systems CVPR 2022
DiSparse: Disentangled Sparsification for Multitask Model Compression CVPR 2022
Controllable Dynamic Multi-Task Architectures CVPR 2022