Learning Context-free Grammars: Capabilities and Limitations of a Recurrent Neural Network with an External Stack Memory (cid:3)

By Sreerupa Das, C. Lee Giles, Guo-Zheng Sun. 1992

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

Citations in the corpus

Long Short-Term Memory-Networks for Machine Reading (2016, background): “A common theme across these models is the use of external memories that interact with a neural controller, whereas our work directly enhances the internal memory of an LSTM for reading and memo-rizing sequences.”
Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets (2015, methodology): “Das et al. (1992) learns a continuous stack which has some similarity with ours.”
Memory Networks (2014, background): “The supporting sentences are labeled as such in the training data for MemNN training (i.e., this is a fully supervised setting).”
Neural Turing Machines (2014, background): “, 2001b) (Das et al., 1992), constructed with recurrent neural networks.”
Analysis Methods in Neural Language Processing: A Survey (2018, background): “A long tradition in work on neural networks is to evaluate and analyze their ability to learn different formal languages (Das et al., 1992; Casey, 1996; Gers and Schmidhuber, 2001; Bodén and Wiles, 2002; Chalup and Blair, 2003).”
Neural Programmer: Inducing Latent Programs with Gradient Descent (2015, background): “While there has been lot of work in augmenting neural networks with additional memory (Das et al., 1992a; Schmidhu-ber, 1993; Hochreiter & Schmidhuber, 1997; Graves et al., 2014; Weston et al., 2015; Kumar et al., 2015; Joulin & Mikolov, 2015), we are not aware of any other work that augments a…”
Learning to Transduce with Unbounded Memory (2015, background): “Previous work has touched on the topic of rendering discrete data structures such as stacks continuous, especially within the context of modelling pushdown automata with neural networks [10, 11, 3].”
On the Binding Problem in Artificial Neural Networks (2020, background): “They are commonly found in RNNs and, when paired with an attention mechanism that attends to a different object at each step, can serve as object representations.”
Transition-Based Dependency Parsing with Stack Long Short-Term Memory (2015, background): “Das et al. (1992) proposed a neural network with an external stack memory based on recurrent neural networks.”
Learning Simple Algorithms from Examples (2015, methodology): “A closely related work to this is (Das et al., 1992), which was recently extended in the Neural DeQue (Grefenstette et al.”
Weakly Supervised Memory Networks (2015, methodology): “We refer to this approach as random noise (RN).”
Variational Memory Addressing in Generative Models (2017, background): “Another line of work which has been gaining popularity recently is memory augmented neural networks [6, 7, 8].”
On Evaluating the Generalization of LSTM Models in Formal Languages (2018, background): “1992; Casey, 1996), context-free (Elman, 1991; Das et al., 1992), and context-sensitive languages (Gers and Schmidhuber, 2001).”
Memory Augmented Recursive Neural Networks (2019, background): “Another line of research proposes to augment recurrent neural networks with speciﬁc data structures such as stacks and queues Das et al. (1992); Sun et al. (2017); Joulin and Mikolov (2015); Grefenstette et al. (2015).”
A Recurrent Neural Network that Learns to Count (1999, methodology): “For example, Das et al. (1992) trained an RNN to activate an explicit reject node for invalid strings.”
A Connectionist Symbol Manipulator that Discovers the Structure of Context-Free Languages (1992, background): “The last grammar could not be learned by their model(Das et al., 1992).”
End-To-End Memory Networks (2015, background): “Subsequent work in the 1990’s explored other types of memory [18, 5, 16].”
Can Recurrent Neural Networks Learn Nested Recursion? (2018, background): “Das et al. (1992) proposed the ﬁrst neural network architecture with a differentiable stack, and used it to learn context-free language.”