research
∙
03/21/2023
A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks
Grokking is a phenomenon where a model trained on an algorithmic task fi...
share
research
∙
10/14/2022
Transparency Helps Reveal When Language Models Learn Meaning
Many current NLP systems are built from language models trained to optim...
research
∙
10/06/2022
Transformers Can Be Expressed In First-Order Logic with Majority
Characterizing the implicit structure of the computation within neural n...
research
∙
09/26/2022
Entailment Semantics Can Be Extracted from an Ideal Language Model
Language models are often trained on text alone, without additional grou...
research
∙
07/02/2022
Log-Precision Transformers are Constant-Depth Uniform Threshold Circuits
We prove that transformer neural networks with logarithmic precision in ...
research
∙
01/28/2022
Extracting Finite Automata from RNNs Using State Merging
One way to interpret the behavior of a blackbox recurrent neural network...
research
∙
06/30/2021
On the Power of Saturated Transformers: A View from Circuit Complexity
Transformers have become a standard architecture for many NLP problems. ...
research
∙
04/22/2021
Provable Limitations of Acquiring Meaning from Ungrounded Form: What will Future Language Models Understand?
Language models trained on billions of tokens have recently led to unpre...
research
∙
04/17/2021
Competency Problems: On Finding and Removing Artifacts in Language Data
Much recent work in NLP has documented dataset artifacts, bias, and spur...
research
∙
02/19/2021
Formal Language Theory Meets Modern NLP
NLP is deeply intertwined with the formal study of language, both concep...
research
∙
10/19/2020
Parameter Norm Growth During Training of Transformers
The capacity of neural networks like the widely adopted transformer is k...
research
∙
04/22/2020
CORD-19: The COVID-19 Open Research Dataset
The COVID-19 Open Research Dataset (CORD-19) is a growing resource of sc...
research
∙
04/18/2020
A Formal Hierarchy of RNN Architectures
We develop a formal hierarchy of the expressive capacity of RNN architec...
research
∙
04/15/2020
On the Linguistic Capacity of Real-Time Counter Automata
Counter machines have achieved a newfound relevance to the field of natu...
research
∙
06/04/2019
Detecting Syntactic Change Using a Neural Part-of-Speech Tagger
We train a diachronic long short-term memory (LSTM) part-of-speech tagge...
research
∙
06/04/2019
Sequential Neural Networks as Automata
This work attempts to explain the types of computation that neural netwo...
research
∙
06/04/2019
Finding Syntactic Representations in Neural Stacks
Neural network architectures have been augmented with differentiable sta...
research
∙
09/08/2018
Context-Free Transductions with Neural Stacks
This paper analyzes the behavior of stack-augmented recurrent neural net...
research
∙
04/18/2018
