activity
20182022
most citedWhat do you learn from context? Probing for sentence structure in contextualized word representations

139 citations · 262 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

13 papers · 1 filter

cs.CL20241 cited

When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1

R. Thomas McCoy, Shunyu Yao, Dan Friedman +2

In "Embers of Autoregression" (McCoy et al., 2023), we showed that several large language models (LLMs) have some important limitations that are attributable to their origins in ne…

cs.CL2020

Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis

Michael A. Lepori, R. Thomas McCoy

As the name implies, contextualized representations of language are typically motivated by their ability to encode context. Which aspects of context are captured by such representa…

cs.CL202015 cited

Universal linguistic inductive biases via meta-learning

R. Thomas McCoy, Erin Grant, Paul Smolensky +2

How do learners acquire languages from the limited data available to them? This process must involve some inductive biases - factors that affect how a learner generalizes - but it…

cs.CL2020

Representations of Syntax [MASK] Useful: Effects of Constituency and Dependency Structure in Recursive LSTMs

Michael A. Lepori, Tal Linzen, R. Thomas McCoy

Sequence-based neural networks show significant sensitivity to syntactic structure, but they still perform less well on syntactic tasks than tree-based networks. Such tree-based ne…

cs.CL202013 cited

Syntactic Data Augmentation Increases Robustness to Inference Heuristics

Junghyun Min, R. Thomas McCoy, Dipanjan Das +2

Pretrained neural models such as BERT, when fine-tuned to perform natural language inference (NLI), often show high accuracy on standard datasets, but display a surprising lack of…

cs.CL20203 cited

Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks

R. Thomas McCoy, Robert Frank, Tal Linzen

Learners that are exposed to the same training data might generalize differently due to differing inductive biases. In neural network models, inductive biases could in theory arise…