activity
20172022
most citedWhat Syntactic Structures block Dependencies in RNN Language Models?

14 citations · 35 across the 6 of their papers we have counts for

collaborators

15 papers

cs.CL20224 cited

When classifying grammatical role, BERT doesn't care about word order... except when it matters

Isabel Papadimitriou, Richard Futrell, Kyle Mahowald

Because meaning can often be inferred from lexical semantics alone, word order is often a redundant cue in natural language. For example, the words chopped, chef, and onion are mor…

cs.CL2021

Sensitivity as a Complexity Measure for Sequence Classification Tasks

Michael Hahn, Dan Jurafsky, Richard Futrell

We introduce a theoretical framework for understanding and predicting the complexity of sequence classification tasks, using a novel extension of the theory of Boolean function sen…

cs.CL2021

Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT

Isabel Papadimitriou, Ethan A. Chi, Richard Futrell +1

We investigate how Multilingual BERT (mBERT) encodes grammar by examining how the high-order grammatical feature of morphosyntactic alignment (how different languages define what c…

cs.CL2020

Predicting cross-linguistic adjective order with information gain

William Dyer, Richard Futrell, Zoey Liu +1

Languages vary in their placement of multiple adjectives before, after, or surrounding the noun, but they typically exhibit strong intra-language tendencies on the relative order o…

cs.CL2020

Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models

Ethan Wilcox, Peng Qian, Richard Futrell +3

Humans can learn structural properties about a word from minimal experience, and deploy their learned syntactic representations uniformly in different grammatical contexts. We asse…

q-bio.NC2020

An information-theoretic account of semantic interference in word production

Richard Futrell

I present a computational-level model of semantic interference effects in word production. Word production is cast as a rate-distortion problem where an agent selects words to mini…