| Challenge: | Existing methods to train multi-task neural networks outperform or even match their single-task counterparts are difficult to implement. |
| Approach: | They propose a method that uses knowledge distillation to train multi-task neural networks that outperform or even match their single-task counterparts. |
| Outcome: | The proposed method outperforms or matches single-task neural networks on the GLUE benchmark. |
Similar Papers
Why Skip If You Can Combine: A Simple Knowledge Distillation Technique for Intermediate Layers (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing knowledge distillation techniques are not suitable for deep learning tasks due to memory constraints. |
| Approach: | They propose to combine knowledge from a large teacher network into a student network (S) they propose to use a combinatorial mechanism to inject layer-level supervision from T to S . |
| Outcome: | The proposed model outperforms existing models in PortugueseEnglish, TurkishEnglish and EnglishGerman directions and students trained using it have 50% fewer parameters and can deliver comparable results to 12-layer teachers. |
Enhancing Task-Specific Distillation in Small Data Regimes through Language Generation (2022.coling-1)
Copied to clipboard
| Challenge: | Large-scale pretrained language models have led to significant improvements in Natural Language Processing, but they come at the cost of high computational and storage requirements. |
| Approach: | They propose to distill knowledge from larger models to smaller ones through pseudo-labels on task-specific datasets. |
| Outcome: | The proposed approach improves on the SST-2, MRPC, YELP-2, and TREC-6 datasets. |
Annealing Knowledge Distillation (2021.eacl-main)
Copied to clipboard
| Challenge: | Knowledge distillation (KD) is a powerful model compression technique for deep neural networks. |
| Approach: | They propose a method to feed the rich information provided by teacher’s soft-targets incrementally and more efficiently by annealing the teacher output incrementally. |
| Outcome: | The proposed method can be used on image classification and NLP language inference tasks with BERT-based models on the GLUE benchmark. |
Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on knowledge distillation have shown that not all knowledge is necessary for learning a good student model. |
| Approach: | They propose an actor-critic approach to selecting appropriate knowledge to transfer during the process of knowledge distillation. |
| Outcome: | The proposed method outperforms several strong knowledge distillation baselines significantly on the GLUE datasets. |
Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings (D19-61)
Copied to clipboard
| Challenge: | Recent research points to knowledge distillation as a potential solution for NLU tasks. |
| Approach: | They propose a training approach that distills large finetuned LMs into a small network using unlabeled training examples. |
| Outcome: | The proposed approach outperforms BERT training approaches while using 300 times fewer parameters. |
One-Teacher and Multiple-Student Knowledge Distillation on Sentiment Classification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing knowledge distillation models require large computing resources and long inference time to perform. |
| Approach: | They propose a one-teacher and multiple-student knowledge distillation approach to distill a deep pre-trained teacher model into multiple shallow student models with ensemble learning. |
| Outcome: | The proposed method achieves better results with fewer parameters and extremely high speedup ratios on three sentiment classification tasks. |
Patient Knowledge Distillation for BERT Model Compression (D19-1)
Copied to clipboard
| Challenge: | Pre-trained language models such as BERT have proven to be highly effective for natural language processing tasks, but the high demand for computing resources hinders their application in practice. |
| Approach: | They propose to compress an original large model (teacher) into an equally-effective lightweight shallow network (student) Empirically, this translates into improved results on multiple NLP tasks with a significant gain in training efficiency, without sacrificing model accuracy. |
| Outcome: | The proposed model reduces the computational cost of training models using the teacher model into a lightweight shallow network. |
Distilling Multilingual Transformers into CNNs for Scalable Intent Classification (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Existing multilingual models for voice assistants are limited by their prohibitive inference time and limited performance. |
| Approach: | They propose to distill and deploy multilingual Transformer models for voice assistants using a teacher-student framework that uses teacher-trained models to supervise student model training. |
| Outcome: | The proposed model outperforms a teacher model trained on unlabelled data and achieves equivalent performance. |
Continual Knowledge Distillation for Neural Machine Translation (2023.acl-long)
Copied to clipboard
| Challenge: | Current parallel corpora are not publicly accessible but trained models are more readily available. |
| Approach: | They propose a method to take advantage of existing translation models to improve one model of interest. |
| Outcome: | The proposed method improves on Chinese-English and German-English datasets and is robust to malicious models. |
XtremeDistil: Multi-stage Distillation for Massive Multilingual Models (2020.acl-main)
Copied to clipboard
| Challenge: | Existing work on pre-trained language models focuses on reducing the size of these models into shallow ones. |
| Approach: | They propose a knowledge distillation technique that leverages teacher internal representations to reduce the size of pre-trained language models. |
| Outcome: | The proposed method outperforms previous methods in multilingual Named Entity Recognition (NER) it reduces the size of teacher models by 35x while retaining 95% of its F1 score. |