activity
20162026
most citedSyntactic Structure from Deep Learning

125 citations · 292 across the 19 of their papers we have counts for

collaborators
Showing cs.CLShow all

39 papers · 1 filter

cs.CL2026

The Emergent Symbolic Structure of Artificial Neural Networks

R. Thomas McCoy, Paul Soulos, Tal Linzen +1

Modern systems in artificial intelligence (AI) somehow excel in domains for which they seem poorly suited. Intelligence has traditionally been modeled as operating over structured…

cs.CL2024

Manipulating language models' training data to study syntactic constraint learning: the case of English passivization

Cara Su-Yi Leong, Tal Linzen

Grammatical rules in natural languages are often characterized by exceptions. How do language learners learn these exceptions to otherwise general patterns? Here, we study this que…

cs.CL2024

SPAWNing Structural Priming Predictions from a Cognitively Motivated Parser

Grusha Prasad, Tal Linzen

Structural priming is a widely used psycholinguistic paradigm to study human sentence representations. In this work we introduce SPAWN, a cognitively motivated parser that can gene…

cs.CL2023

Do Language Models' Words Refer?

Matthew Mandelkern, Tal Linzen

What do language models (LMs) do with language? Everyone agrees that they can produce sequences of (mostly) coherent strings of English. But do those sentences mean something, or a…

cs.CL2022

Causal Analysis of Syntactic Agreement Neurons in Multilingual Language Models

Aaron Mueller, Yu Xia, Tal Linzen

Structural probing work has found evidence for latent syntactic information in pre-trained language models. However, much of this analysis has focused on monolingual models, and an…

cs.CL20221 cited

When a sentence does not introduce a discourse entity, Transformer-based models still sometimes refer to it

Sebastian Schuster, Tal Linzen

Understanding longer narratives or participating in conversations requires tracking of discourse entities that have been mentioned. Indefinite noun phrases (NPs), such as 'a dog',…