arXiv (Cornell University) · 2019 · 20 citations · 15 references
ComputingComputer ScienceKnowledge RepresentationMachine LearningNatural Language ProcessingDeep LearningLanguage ModelingLanguage ModelsMachine TranslationNeural NetworksWord EmbeddingsKnowledge DistillationLanguage Model PretrainingNeural Language ModelsNeural Machine Translation
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high performance can be explained by efficient knowledge representation of deep learning models. While many methods have been proposed to learn more efficient representation, knowledge distillation from pretrained deep networks suggest that we can use more information from the soft target probability to train other neural networks. In this paper, we propose a new knowledge distillation method self-knowledge distillation, based on the soft target probabilities of the training model itself, where multimode information is distilled from the word embedding space right below the softmax layer. Due to the time complexity, our method approximates the soft target probabilities. In experiments, we applied the proposed method to two different and fundamental NLP tasks: language model and neural machine translation. The experiment results show that our proposed method improves performance on the tasks.
15
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
YOLO9000: Better, Faster, Stronger
Joseph Redmon, Ali Farhadi · 2017 · 19K citations
Distilling the Knowledge in a Neural Network
Geoffrey E. Hinton, Oriol Vinyals · arXiv (Cornell University) · 2015 · 14K citations · Full text
Efficient Estimation of Word Representations in Vector Space
Tomáš Mikolov, Kai Chen, Greg S. Corrado et al. · arXiv (Cornell University) · 2013 · 11.7K citations · Full text