no code implementations • 19 May 2022 • Gehui Shen, Shibo Jie, Ziheng Li, Zhi-Hong Deng
In our framework, a generative classifier which utilizes replay memory is used for inference, and the training objective is a pair-based metric learning loss which is proven theoretically to optimize the feature space in a generative way.
no code implementations • 10 Jun 2020 • Song Zhang, Gehui Shen, Jinsong Huang, Zhi-Hong Deng
Lifelong or continual learning remains to be a challenge for artificial neural network, as it is required to be both stable for preservation of old knowledge and plastic for acquisition of new knowledge.
no code implementations • 7 May 2020 • Gehui Shen, Song Zhang, Xiang Chen, Zhi-Hong Deng
For this scenario, generative replay is a promising strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting.
1 code implementation • 28 May 2019 • Ting Huang, Gehui Shen, Zhi-Hong Deng
Compared to previous models which can also skip words, our model achieves better trade-offs between performance and efficiency.
no code implementations • 18 Aug 2018 • Gehui Shen, Zhi-Hong Deng, Ting Huang, Xi Chen
Recursive Neural Network (RecNN), a type of models which compose words or phrases recursively over syntactic tree structures, has been proven to have superior ability to obtain sentence representation for a variety of NLP tasks.
no code implementations • 2 Jun 2018 • Xi Chen, Zhi-Hong Deng, Gehui Shen, Ting Huang
This paper proposes a novel framework for recurrent neural networks (RNNs) inspired by the human memory models in the field of cognitive neuroscience to enhance information processing and transmission between adjacent RNNs' units.
no code implementations • 27 Dec 2017 • Zhiqing Sun, Gehui Shen, Zhi-Hong Deng
However, if we consider segmenting a given sentence, the most intuitive idea is to predict whether to segment for each gap between two consecutive characters, which in comparison makes previous approaches seem too complex.
no code implementations • EMNLP 2017 • Gehui Shen, Yunlun Yang, Zhi-Hong Deng
Sentence pair modeling is a crucial problem in the field of natural language processing.