RNN/CNN-based Encoder-Decoder Neural Network

An RNN/CNN-based Encoder-Decoder Neural Network is an encoder-decoder neural network that consists of a RNN-based encoder neural network and a CNN-based decoder neural network.

• Context:
  • It can be trained by a RNN/CNN-based Encoder-Decoder Model Training System (that implements an RNN/CNN-based encoder/decoder model training algorithm).
  • It can be instantiated in a Trained RNN/CNN-based Encoder/Decoder Network.
  • …
• Example(s):
  • the one proposed in Tang et al. (2018).
  • …
• Counter-Example(s):
  • an RNN/RNN-based Encoder-Decoder Network.
  • an CNN/CNN-based Encoder-Decoder Network.
• See: Neural seq2seq, Neural Encoder/Decoder Model Training System, Mixed-Style Encoder/Decoder Network, Sequence-to-Sequence Learning, Bidirectional Neural Network.

---

---

References

2018

• (Tang et al., 2018) ⇒ Shuai Tang, Hailin Jin, Chen Fang, Zhaowen Wang, and Virginia R. de Sa. (2018). “Exploring Asymmetric Encoder-decoder Structure for Context-based Sentence Representation Learning.”
  • QUOTE: ... As a result, we build an encoder-decoder architecture with an RNN encoder and a CNN decoder, and we show that neither an autoregressive decoder nor an RNN decoder is required. We further combine a suite of effective designs to significantly improve model efficiency while also achieving better performance. Our model is trained on two different large unlabeled corpora, and in both cases transferability is evaluated on a set of downstream language understanding tasks. ...

---