activity
20182026
most citedMeasuring and Improving Consistency in Pretrained Language Models

33 citations · 127 across the 31 of their papers we have counts for

collaborators
Showing 2020Show all

5 papers · 1 filter

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…

cs.CL2020

Unsupervised Distillation of Syntactic Information from Contextualized Word Representations

Shauli Ravfogel, Yanai Elazar, Jacob Goldberger +1

Contextualized word representations, such as ELMo and BERT, were shown to perform well on various semantic and syntactic tasks. In this work, we tackle the task of unsupervised dis…

cs.CL2020★ 6 cited

Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals

Yanai Elazar, Shauli Ravfogel, Alon Jacovi +1

A growing body of work makes use of probing to investigate the working of neural models, often considered black boxes. Recently, an ongoing debate emerged surrounding the limitatio…

cs.CL2020★ 1 cited

Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection

Shauli Ravfogel, Yanai Elazar, Hila Gonen +2

The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models.…