Loading...
Please wait, while we are loading the content...
Similar Documents
Multi-Timescale Long Short-Term Memory Neural Network for Modelling Sentences and Documents
| Content Provider | CiteSeerX |
|---|---|
| Author | Liu, Pengfei Qiu, Xipeng Chen, Xinchi Wu, Shiyu Huang, Xuanjing |
| Abstract | Neural network based methods have ob-tained great progress on a variety of nat-ural language processing tasks. However, it is still a challenge task to model long texts, such as sentences and documents. In this paper, we propose a multi-timescale long short-termmemory (MT-LSTM) neu-ral network to model long texts. MT-LSTM partitions the hidden states of the standard LSTM into several groups. Each group is activated at different time peri-ods. Thus, MT-LSTM can model very long documents as well as short sentences. Experiments on four benchmark datasets show that our model outperforms the other neural models in text classification task. 1 |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Modelling Sentence Long Text Challenge Task Long Document Different Time Peri-ods Short Sentence Neural Model Several Group Text Classification Task Standard Lstm Hidden State Mt-lstm Partition Benchmark Datasets Neu-ral Network Multi-timescale Long Short-termmemory Neural Network Great Progress Nat-ural Language Processing Task |
| Content Type | Text |
