activity
20182022
most citedReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension

3 citations · 3 across the 2 of their papers we have counts for

collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2021

Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?

William Merrill, Yoav Goldberg, Roy Schwartz +1

Language models trained on billions of tokens have recently led to unprecedented results on many NLP tasks. This success raises the question of whether, in principle, a system can…

cs.CL2021

Formal Language Theory Meets Modern NLP

William Merrill

NLP is deeply intertwined with the formal study of language, both conceptually and historically. Arguably, this connection goes all the way back to Chomsky's Syntactic Structures i…

cs.CL2020

A Formal Hierarchy of RNN Architectures

William Merrill, Gail Weiss, Yoav Goldberg +3

We develop a formal hierarchy of the expressive capacity of RNN architectures. The hierarchy is based on two formal properties: space complexity, which measures the RNN's memory, a…

cs.CL2019

Detecting Syntactic Change Using a Neural Part-of-Speech Tagger

William Merrill, Gigi Felice Stark, Robert Frank

We train a diachronic long short-term memory (LSTM) part-of-speech tagger on a large corpus of American English from the 19th, 20th, and 21st centuries. We analyze the tagger's abi…

cs.CL2019

Finding Syntactic Representations in Neural Stacks

William Merrill, Lenny Khazan, Noah Amsel +3

Neural network architectures have been augmented with differentiable stacks in order to introduce a bias toward learning hierarchy-sensitive regularities. It has, however, proven d…

cs.CL2019

Sequential Neural Networks as Automata

William Merrill

This work attempts to explain the types of computation that neural networks can perform by relating them to automata. We first define what it means for a real-time network with bou…