Adina Williams

Adina is a Postdoctoral Researcher at Facebook AI Research in NYC. She previously earned her Ph.D. at New York University's Department of Linguistics, where she investigated the brain basis of syntactic and semantic processing. Adina has authored papers on formal linguistic theory, cognitive neuroscience of language, and natural language processing. Her current focus is on dataset creation and evaluation for natural language inference models, as well as investigating grammatical gender in the context of mitigating bias and increasing fairness in AI, and in deepening our scientific understanding of complex morphological phenomena such as classifiers and inflection classes.

Adina's Publications

May 03, 2020

RESEARCH

NLP

Quantifying the Semantic Core of Gender Systems

Many of the world’s languages employ grammatical gender on the lexeme. For example, in Spanish, the word for house (casa) is feminine, whereas the word for paper (papel) is masculine. To a speaker of a genderless language, this assignment seems…

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

May 03, 2020

May 03, 2020

RESEARCH

NLP

On the Idiosyncrasies of the Mandarin Chinese Classifier System

While idiosyncrasies of the Chinese classifier system have been a richly studied topic among linguists (Adams and Conklin, 1973; Erbaugh, 1986; Lakoff, 1986), not much work has been done to quantify them with statistical methods. In this paper,…

Shijia Liu, Hongyuan Mei, Adina Williams, Ryan Cotterell,

May 03, 2020

May 03, 2020

RESEARCH

NLP

XNLI: Evaluating Cross-lingual Sentence Representations

State-of-the-art natural language processing systems rely on supervision in the form of annotated data to learn competent models. These models are generally trained on data in a single language (usually English), and cannot be directly used…

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

May 03, 2020