activity
20182022
most citedStudying the Inductive Biases of RNNs with Synthetic Variations of Natural Languages

10 citations · 14 across the 3 of their papers we have counts for

collaborators

11 papers

cs.CL20223 cited

DALLE-2 is Seeing Double: Flaws in Word-to-Concept Mapping in Text2Image Models

Royi Rassin, Shauli Ravfogel, Yoav Goldberg

We study the way DALLE-2 maps symbols (words) in the prompt to their references (entities or properties of entities in the generated image). We show that in stark contrast to the w…

cs.CL2021

Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction

Shauli Ravfogel, Grusha Prasad, Tal Linzen +1

When language models process syntactically complex sentences, do they use their representations of syntax in a manner that is consistent with the grammar of the language? We propos…

cs.CL2021

Contrastive Explanations for Model Interpretability

Alon Jacovi, Swabha Swayamdipta, Shauli Ravfogel +3

Contrastive explanations clarify why an event occurred in contrast to another. They are more inherently intuitive to humans to both produce and comprehend. We propose a methodology…

cs.CL2021

Measuring and Improving Consistency in Pretrained Language Models

Yanai Elazar, Nora Kassner, Shauli Ravfogel +4

Consistency of a model -- that is, the invariance of its behavior under meaning-preserving alternations in its input -- is a highly desirable property in natural language processin…

cs.CL2020

It's not Greek to mBERT: Inducing Word-Level Translations from Multilingual BERT

Hila Gonen, Shauli Ravfogel, Yanai Elazar +1

Recent works have demonstrated that multilingual BERT (mBERT) learns rich cross-lingual representations, that allow for transfer across languages. We study the word-level translati…

cs.CL2020

The Extraordinary Failure of Complement Coercion Crowdsourcing

Yanai Elazar, Victoria Basmov, Shauli Ravfogel +2

Crowdsourcing has eased and scaled up the collection of linguistic annotation in recent years. In this work, we follow known methodologies of collecting labeled data for the comple…