← Application Areas
Machine Learning › Application Areas ›

Model Compression

1503 directly classified papers

Papers per year

Papers

Compressing 1D Time-Channel Separable Convolutions Using Sparse Random Ternary Matrices INTERSPEECH 2021
Extremely Low Footprint End-to-End ASR System for Smart Device INTERSPEECH 2021
PQK: Model Compression via Pruning, Quantization, and Knowledge Distillation INTERSPEECH 2021
Continual Learning in Task-Oriented Dialogue Systems EMNLP 2021
FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations EMNLP 2021
Efficient Inference for Multilingual Neural Machine Translation EMNLP 2021
Block Pruning For Faster Transformers EMNLP 2021
NewsBERT: Distilling Pre-trained Language Model for Intelligent News Application EMNLP 2021
MSD: Saliency-aware Knowledge Distillation for Multimodal Understanding EMNLP 2021
Subformer: Exploring Weight Sharing for Parameter Efficiency in Generative Transformers EMNLP 2021
Block-wise Word Embedding Compression Revisited: Better Weighting and Structuring EMNLP 2021
Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoders EACL 2021
cushLEPOR: customising hLEPOR metric using Optuna for higher agreement with human judgments or pre-trained language model LaBSE EMNLP 2021
Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search IJCNLP 2021
GhostBERT: Generate More Features with Cheap Operations for BERT IJCNLP 2021
MATE-KD: Masked Adversarial TExt, a Companion to Knowledge Distillation IJCNLP 2021
fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP IJCNLP 2021
Direction is what you need: Improving Word Embedding Compression in Large Language Models IJCNLP 2021
Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains ACL 2021
RankDistil: Knowledge Distillation for Ranking AISTATS 2021
Interpretable Embedding Procedure Knowledge Transfer via Stacked Principal Component Analysis and Graph Neural Network AAAI 2021
Winning Lottery Tickets in Deep Generative Models AAAI 2021
Cross-Layer Distillation with Semantic Calibration AAAI 2021
Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks AAAI 2021
Frivolous Units: Wider Networks Are Not Really That Wide AAAI 2021