Theoretical Conditions and Empirical Failure of Bracket Counting on Long
Sequences with Linear Recurrent Networks

Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks

7 April 2023

Nadine El-Naggar

Pranava Madhyastha

ArXiv (abs)PDF HTML

Papers citing "Theoretical Conditions and Empirical Failure of Bracket Counting on Long Sequences with Linear Recurrent Networks"

7 / 7 papers shown

Title
Exploring the Long-Term Generalization of Counting Behavior in RNNs Nadine El-Naggar Pranava Madhyastha Tillman Weyde 38 5 0 29 Nov 2022
Compositional Generalization via Neural-Symbolic Stack Machines Xinyun Chen Chen Liang Adams Wei Yu Basel Alomair Denny Zhou BDL 67 101 0 15 Aug 2020
On the Linguistic Capacity of Real-Time Counter Automata William Merrill 48 23 0 15 Apr 2020
Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages Mirac Suzgun Sebastian Gehrmann Yonatan Belinkov Stuart M. Shieber 66 50 0 08 Nov 2019
LSTM Networks Can Perform Dynamic Counting Mirac Suzgun Sebastian Gehrmann Yonatan Belinkov Stuart M. Shieber 76 75 0 09 Jun 2019
Sequential Neural Networks as Automata William Merrill 73 78 0 04 Jun 2019
Inferring Algorithmic Patterns with Stack-Augmented Recurrent Nets Armand Joulin Tomas Mikolov TPM 144 412 0 03 Mar 2015