People

Adina Williams

Research Scientist

Adina is a Research Scientist at Facebook AI Research in NYC (started October 2018). Previously, she earned her PhD at New York University in the Department of Linguistics, where she investigated the brain basis of syntactic and semantic processing. Her main research goal is to strengthen the connections between linguistics and cognitive science on the one hand and natural language processing and artificial intelligence on the other. She approaches this process from both directions: she brings linguistic and cognitive scientific insights about human language to bear on training, evaluating, and debiasing NLP systems, and also applies statistical methods and corpus analytic tools from NLP to uncover new quantitative, cross-linguistic facts about particular human languages.

Interests

NLP, formal linguistics, semantics, parsing, crowdsourcing and annotation for NLP, natural language inference, grammar induction and cognitive neuroscience of language

Latest Publications

EMNLP - November 16, 2020

Measuring the Similarity of Grammatical Gender Systems by Comparing Partitions

Arya D. McCarthy, Adina Williams, Shijia Liu, David Yarowsky, Ryan Cotterell

TACL - July 31, 2020

On the Relationships Between the Grammatical Genders of Inanimate Nouns and Their Co-Occurring Adjectives and Verbs

Adina Williams, Ryan Cotterell, Lawrence Wolf-Sonkin, Damián E. Blasi, Hanna Wallach

ACL - July 6, 2020

Information-Theoretic Probing for Linguistic Structure

Tiago Pimentel, Josef Valvoda, Rowan Hall Maudslay, Ran Zmigrod, Adina Williams, Ryan Cotterell

ACL - June 19, 2020

Are Natural Language Inference Models IMPPRESsive? Learning IMPlicature and PRESupposition

Paloma Jeretič, Alex Warstadt, Suvrat Bhooshan, Adina Williams

ACL - June 19, 2020

Predicting Declension Class from Form and Meaning

Adina Williams, Tiago Pimentel, Arya D. McCarthy, Hagen Blix, Eleanor Chodroff, Ryan Cotterell

ACL - June 19, 2020

A Tale of a Probe and a Parser

Rowan Hall Maudslay, Josef Valvoda, Tiago Pimentel, Adina Williams, Ryan Cotterell

ACL - June 5, 2020

Adversarial NLI: A New Benchmark for Natural Language Understanding

Yixin Nie, Adina Williams, Emily Dinan, Mohit Bansal, Jason Weston, Douwe Kiela

EMNLP - November 4, 2019

Quantifying the Semantic Core of Gender Systems

Adina Williams, Ryan Cotterell, Lawrence Wolf-Sonkin, Damián E. Blasi, Hanna Wallach

NAACL - June 16, 2019

On the Idiosyncrasies of the Mandarin Chinese Classifier System

Shijia Liu, Hongyuan Mei, Adina Williams, Ryan Cotterell

EMNLP 2018 - October 29, 2018

XNLI: Evaluating Cross-lingual Sentence Representations

Alexis Conneau, Ruty Rinott, Guillaume Lample, Adina Williams, Samuel R. Bowman, Holger Schwenk, Ves Stoyanov