Xin Guo


pdf bib
基于迭代信息传递和滑动窗口注意力的问题生成模型研究(Question Generation Model Based on Iterative Message Passing and Sliding Windows Hierarchical Attention)
Qian Chen (陈千) | Xiaoying Gao (高晓影) | Suge Wang (王素格) | Xin Guo (郭鑫)
Proceedings of the 20th Chinese National Conference on Computational Linguistics



pdf bib
Continual Learning Long Short Term Memory
Xin Guo | Yu Tian | Qinghan Xue | Panos Lampropoulos | Steven Eliuk | Kenneth Barner | Xiaolong Wang
Findings of the Association for Computational Linguistics: EMNLP 2020

Catastrophic forgetting in neural networks indicates the performance decreasing of deep learning models on previous tasks while learning new tasks. To address this problem, we propose a novel Continual Learning Long Short Term Memory (CL-LSTM) cell in Recurrent Neural Network (RNN) in this paper. CL-LSTM considers not only the state of each individual task’s output gates but also the correlation of the states between tasks, so that the deep learning models can incrementally learn new tasks without catastrophically forgetting previously tasks. Experimental results demonstrate significant improvements of CL-LSTM over state-of-the-art approaches on spoken language understanding (SLU) tasks.