Recurrent Neural Network (RNN)-based Encoder

A Recurrent Neural Network (RNN)-based Encoder is an encoder neural network that is based on a RNN architecture.

• Context:
  • It can be trained by an RNN Encoder Training System (that solves an RNN encoder training task).
  • …
• Example(s):
  • an Encoder GRU-RNN, an Encoder LSTM-RNN.
  • an RNN-based Text Encoder, ..
  • …
• Counter-Example(s):
  • a Decoder Neural Network,
  • an Encoder Convolutional Neural Network,
  • an Attention Encoder RNN,
  • a Neural Auto-Encoding Network.
• See: Neural Machine Translation System, Text Error Correction System, WikiText Error Correction System, Seq2Seq Neural Network, Natural Language Processing System.

---

---

References

2017a

• (Chen et al., 2017) ⇒ Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, and Diana Inkpen (2017). "Recurrent Neural Network-based Sentence Encoder with Gated Attention for Natural Language Inference'. In: arXiv preprint arXiv:1708.01353.

2917b

• (Su et al., 2017b) ⇒ Jinsong Su, Zhixing Tan, Deyi Xiong, Rongrong Ji, Xiaodong Shi, and Yang Liu (2017, February). "Lattice-based Recurrent Neural Network Encoders for Neural Machine Translation". In: Proceedings of the AAAI Conference on Artificial Intelligence.

---