Zhizhong Ma

Large Margin Training for Long Short-Term Memory Neural Networks in Neural Language Modeling

2022 · 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI)

Language models based on Long Short-Term Memory (LSTM) neural networks have been widely applied to automatic speech recognition, natural language processing research. However, current LSTMs are trained by employing the cross-entropy loss function, which only …