activity
20162023
most citedAssessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies

27 citations · 31 across the 6 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2023

A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing

William Timkey, Tal Linzen

Two of the central factors believed to underpin human sentence processing difficulty are expectations and retrieval from working memory. A recent attempt to create a unified cognit…

cs.CL20232 cited

Verb Conjugation in Transformers Is Determined by Linear Encodings of Subject Number

Sophie Hao, Tal Linzen

Deep architectures such as Transformers are sometimes criticized for having uninterpretable "black-box" representations. We use causal intervention analysis to show that, in fact,…

cs.CL2023

SLOG: A Structural Generalization Benchmark for Semantic Parsing

Bingzhi Li, Lucia Donatelli, Alexander Koller +3

The goal of compositional generalization benchmarks is to evaluate how well models generalize to new complex linguistic expressions. Existing benchmarks often focus on lexical gene…

cs.CL20232 cited

How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases

Aaron Mueller, Tal Linzen

Accurate syntactic representations are essential for robust generalization in natural language. Recent work has found that pre-training can teach language models to rely on hierarc…

cs.CL2021

Improving Compositional Generalization with Latent Structure and Data Augmentation

Linlu Qiu, Peter Shaw, Panupong Pasupat +4

Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization. Compositional data augmentation via example recombination has…

cs.CL201627 cited

Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies

Tal Linzen, Emmanuel Dupoux, Yoav Goldberg

The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Ling…