1

Let's talk (efficiently) about us: Person systems achieve near-optimal compression

Noga Zaslavsky*, Mora Maldonado*, Jennifer Culbertson
2021 CogSci
PDF Proceedings

Competition from novel features drives scalar inferences in reference games

Jennifer Hu, Noga Zaslavsky, Roger P. Levy
2021 CogSci
PDF Code Proceedings

Probing artificial neural networks: insights from neuroscience

Anna A. Ivanova, John Hewitt, Noga Zaslavsky
2021 ICLR Brain2AI Workshop
PDF ICLR Workshop

Cloze Distillation: Improving Neural Language Models with Human Next-Word Prediction

Tiwalayo Eisape, Noga Zaslavsky, Roger Levy
2020 CoNLL
PDF DOI

Toward human-like object naming in artificial neural systems

Tiwalayo Eisape, Roger Levy, Joshua Tenenbaum, Noga Zaslavsky
2020 BAICS @ ICLR
PDF Video ICLR Workshop

Semantic categories of artifacts and animals reflect efficient coding

Noga Zaslavsky, Terry Regier, Naftali Tishby, Charles Kemp
2019 CogSci
PDF

Color naming reflects both perceptual structure and communicative need (earlier version)

Best paper award for computational modeling of language
Noga Zaslavsky, Charles Kemp, Naftali Tishby, Terry Regier
2018 CogSci
PDF

Efficient human-like semantic representations via the Information Bottleneck principle

Noga Zaslavsky, Charles Kemp, Terry Regier, Naftali Tishby
2017 CIAI @ NeurIPS
PDF NeurIPS Workshop

Deep learning and the Information Bottleneck principle

Naftali Tishby, Noga Zaslavsky
2015 ITW
PDF DOI