activity
20202022
most citedWhen classifying grammatical role, BERT doesn't care about word order... except when it matters

4 citations · 5 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CL20221 cited

Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality

Anuj Diwan, Layne Berry, Eunsol Choi +2

Recent visuolinguistic pre-trained models show promising progress on various end tasks such as image retrieval and video captioning. Yet, they fail miserably on the recently propos…

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

A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space

Alex Jones, William Yang Wang, Kyle Mahowald

In cross-lingual language models, representations for many different languages live in the same space. Here, we investigate the linguistic and non-linguistic factors affecting sent…

cs.CL2021

How (Non-)Optimal is the Lexicon?

Tiago Pimentel, Irene Nikkarinen, Kyle Mahowald +2

The mapping of lexical meanings to wordforms is a major feature of natural languages. While usage pressures might assign short words to frequent meanings (Zipf's law of abbreviatio…

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

With Little Power Comes Great Responsibility

Dallas Card, Peter Henderson, Urvashi Khandelwal +3

Despite its importance to experimental design, statistical power (the probability that, given a real effect, an experiment will reject the null hypothesis) has largely been ignored…