Evaluating the Ability of LSTMs to Learn Context-Free Grammars

6 November 2018

Papers citing "Evaluating the Ability of LSTMs to Learn Context-Free Grammars"

5 / 5 papers shown

Title
Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions S. Bhattamishra Arkil Patel Varun Kanade Phil Blunsom 22 44 0 22 Nov 2022
Assessing the Unitary RNN as an End-to-End Compositional Model of Syntax Jean-Philippe Bernardy Shalom Lappin 32 1 0 11 Aug 2022
Thinking Like Transformers Gail Weiss Yoav Goldberg Eran Yahav AI4CE 35 127 0 13 Jun 2021
On the Computational Power of Transformers and its Implications in Sequence Modeling S. Bhattamishra Arkil Patel Navin Goyal 33 64 0 16 Jun 2020
Memory-Augmented Recurrent Neural Networks Can Learn Generalized Dyck Languages Mirac Suzgun Sebastian Gehrmann Yonatan Belinkov Stuart M. Shieber 16 50 0 08 Nov 2019