Context-Free Transductions with Neural Stacks

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.

Repositories linked to this paper

viking-sudo-rm/StackNN — marked official in Papers with Code; named in the paper
suzgunmirac/marnns

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1809.02836")
get_code_for_paper("1809.02836")
have("1809.02836")

Connect an agent — have() is free.