The Neural Network Pushdown Automaton: Architecture, Dynamics and Training

By Guo-Zheng Sun, C. Lee Giles, Hsing-Hen Chen. 1997

Subfields: Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Model Architectures

1. Kyunghyun Cho
2. Chris Dyer
3. Yoshua Bengio
4. Yoav Goldberg
5. Miguel Ballesteros
6. Caglar Gulcehre
7. Noah A. Smith
8. Graham Neubig

Citations in the corpus

• Recurrent Neural Network Grammars (2016, background): “the first work to use syntactically structured neural models to generate language. Earlier work has demonstrated that sequential RNNs have the capacity to recognize contextfree (and beyond) languages (Sun et al., 1998; Siegelmann and Sontag, 1995). In contrast, our work may be understood as a way of ”
• Dynamic Neural Turing Machine with Continuous and Discrete Addressing Schemes (2018, background): “Grefenstette, Hermann, Suleyman, and Blunsom (2015), Joulin and Mikolov (2015), and Sun, Giles, and Chen (1997) proposed a continuous, differentiable stack.”
• Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes (2016, background): “In [21, 22, 12], a continuous, differentiable stack was proposed.”