mlsanityData to 14 Oct 2026

Context-Free Transductions with Neural Stacks

arXiv 1809.02836 ↗First posted 8 Sep 2018cs.NE cs.CL cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

This paper analyzes the behavior of stack-augmented recurrent neural network (RNN) models. Due to the architectural similarity between stack RNNs and pushdown transducers, we train stack RNN models on a number of tasks, including string reversal, context-free language modelling, and cumulative XOR evaluation. Examining the behavior of our networks, we show that stack-augmented RNNs can discover intuitive stack-based strategies for solving our tasks. However, stack RNNs are more difficult to train than classical architectures such as LSTMs. Rather than employ stack-based strategies, more complex networks often find approximate solutions by using the stack as unstructured memory.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). First posted on arXiv 8 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 2; 2023: 2; 2024: 7.

14 papers.

Sort:

  1. 2022Neural Networks and the Chomsky Hierarchycited by 217
  2. 2024Mission: Impossible Language Modelscited by 32
  3. 2024Transformers Can Represent n-gram Language Modelscited by 32
  4. 2024What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languagescited by 20
  5. 2021Learning Hierarchical Structures with Differentiable Nondeterministic Stackscited by 16
  6. 2021Formal Language Theory Meets Modern NLPcited by 9
  7. 2021Learning Bounded Context-Free-Grammar via LSTM and the Transformer:Difference and Explanationscited by 7
  8. 2023Recurrent Neural Language Models as Probabilistic Finite-state Automatacited by 6
  9. 2024Lower Bounds on the Expressivity of Recurrent Neural Language Modelscited by 4
  10. 2022State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictionscited by 2
  11. 2024A Transformer with Stack Attentioncited by 2
  12. 2023On the Representational Capacity of Recurrent Neural Language Modelscited by 1
2 more
  1. 2024On Efficiently Representing Regular Languages as RNNscited by 1
  2. 2024Enhancing Length Extrapolation in Sequential Models with Pointer-Augmented Neural Memorycited by 0